{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "25cf0a40e669a70",
   "metadata": {},
   "source": [
    "# Understanding Ontologies with Cognee\n",
    "\n",
    "This notebook demonstrates how to work with ontologies in scientific research using the Cognee framework. We'll explore how ontologies can enhance our understanding and querying of scientific papers.\n",
    "\n",
    "## What is an Ontology?\n",
    "\n",
    "An ontology is a formal representation of knowledge that defines:\n",
    "- Concepts within a domain\n",
    "- Relationships between concepts\n",
    "- Properties and attributes\n",
    "- Rules and constraints\n",
    "\n",
    "Key terms:\n",
    "- **Classes**: Categories or types (e.g., Disease, Symptom)\n",
    "- **Instances**: Specific examples of classes (e.g., Type 2 Diabetes)\n",
    "- **Properties**: Relationships between classes/instances (e.g., hasSymptom)\n",
    "- **Axioms**: Logical statements defining relationships"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "441248da37f2b901",
   "metadata": {},
   "source": [
    "## Setup\n",
    "\n",
    "First, let's install the required packages and set up our environment:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "8cf7ba29f9a150af",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-03-26T16:17:55.937140Z",
     "start_time": "2025-03-26T16:17:55.908542Z"
    }
   },
   "outputs": [],
   "source": [
    "# Install required package\n",
    "# !pip install cognee"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "d825d126b3a0ec26",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-03-26T16:18:09.382400Z",
     "start_time": "2025-03-26T16:18:09.342349Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:23:32.523592\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDeleted old log file: /Users/borisarzentar/Projects/Topoteretes/cognee/logs/2025-06-18_20-08-11.log\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
      "\n",
      "\u001b[2m2025-06-18T18:23:32.524072\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mLogging initialized           \u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m \u001b[36mcognee_version\u001b[0m=\u001b[35m0.1.42-dev\u001b[0m \u001b[36mos_info\u001b[0m=\u001b[35m'Darwin 24.5.0 (Darwin Kernel Version 24.5.0: Tue Apr 22 19:54:25 PDT 2025; root:xnu-11417.121.6~2/RELEASE_ARM64_T6020)'\u001b[0m \u001b[36mpython_version\u001b[0m=\u001b[35m3.11.5\u001b[0m \u001b[36mstructlog_version\u001b[0m=\u001b[35m25.4.0\u001b[0m\n",
      "\n",
      "\u001b[1mHTTP Request: GET https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json \"HTTP/1.1 200 OK\"\u001b[0m\n",
      "/Users/borisarzentar/Projects/Topoteretes/cognee/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
      "  from .autonotebook import tqdm as notebook_tqdm\n",
      "/Users/borisarzentar/Projects/Topoteretes/cognee/.venv/lib/python3.11/site-packages/dlt/helpers/dbt/__init__.py:3: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.\n",
      "  import pkg_resources\n"
     ]
    }
   ],
   "source": [
    "# Import required libraries\n",
    "import os\n",
    "import cognee\n",
    "from cognee.shared.logging_utils import get_logger\n",
    "from cognee.api.v1.search import SearchType\n",
    "\n",
    "logger = get_logger()\n",
    "\n",
    "# Set up OpenAI API key (required for Cognee's LLM functionality)\n",
    "os.environ[\"LLM_API_KEY\"] = \"your-api-key-here\"  # Replace with your API key"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "6af350837e86b7a1",
   "metadata": {},
   "source": [
    "## Creating the Pipeline\n",
    "\n",
    "Let's create a pipeline that will:\n",
    "1. Clean existing data\n",
    "2. Process scientific papers\n",
    "3. Apply ontological knowledge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "4d0e4a58e4207a7d",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T17:12:54.006718Z",
     "start_time": "2025-04-09T17:12:53.992906Z"
    }
   },
   "outputs": [],
   "source": [
    "async def run_pipeline(ontology_path=None):\n",
    "    # Clean existing data\n",
    "    await cognee.prune.prune_data()\n",
    "    await cognee.prune.prune_system(metadata=True)\n",
    "    \n",
    "    # Set up path to scientific papers\n",
    "    scientific_papers_dir = os.path.join(\n",
    "        os.path.dirname(os.path.dirname(os.path.abspath(\".\"))), \n",
    "        \"cognee\",\n",
    "        \"examples\",\n",
    "        \"data\", \n",
    "        \"scientific_papers/\"\n",
    "    )\n",
    "    \n",
    "    # Add papers to the system\n",
    "    await cognee.add(scientific_papers_dir)\n",
    "    \n",
    "    # Cognify with optional ontology\n",
    "    return await cognee.cognify(ontology_file_path=ontology_path)\n",
    "\n",
    "async def query_pipeline(questions):\n",
    "    answers = []\n",
    "    for question in questions:\n",
    "        search_results = await cognee.search(\n",
    "            query_type=SearchType.GRAPH_COMPLETION,\n",
    "            query_text=question,\n",
    "        )\n",
    "        answers.append(search_results)\n",
    "    return answers"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c87c21a75d6f4d79",
   "metadata": {},
   "source": [
    "## Running the Demo\n",
    "\n",
    "Let's test our system with some medical questions, comparing results with and without ontological knowledge:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1363772d2b48f5c0",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T17:14:31.818452Z",
     "start_time": "2025-04-09T17:12:55.491598Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:23:36.293948\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCleared all data from graph while preserving structure\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:36.358529\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "--- Results WITH ontology ---\n",
      "\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[1mLangfuse client is disabled since no public_key was provided as a parameter or environment variable 'LANGFUSE_PUBLIC_KEY'. See our docs: https://langfuse.com/docs/sdk/python/low-level-sdk#initialize-client\u001b[0m\u001b[92m20:23:36 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:37 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\n",
      "\u001b[1mEmbeddingRateLimiter initialized: enabled=False, requests_limit=60, interval_seconds=60\u001b[0m\u001b[92m20:23:37 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:37 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.051934\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `2bec40b8-e3d1-54ab-bfc5-eb5d4695ce63`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.052396\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.053449\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "User c0d22401-0c0b-40ad-8ce5-8d6094b0461d has registered.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:23:38.501726\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.502195\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.502710\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `2bec40b8-e3d1-54ab-bfc5-eb5d4695ce63`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.504289\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'examples/python/ontology_input_example/enriched_medical_ontology_with_classes.owl' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.513310\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `ba0e59ba-8966-58b2-8dbe-0d3d5009b268`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.513615\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.513906\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.517146\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:38.799196\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:38 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:23:49 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:49 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:56 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:56 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:57 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:57 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:59 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:23:59 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.600042\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.600534\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.600963\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular health' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.601349\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.601735\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hypertension' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.602104\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'heart failure' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.602479\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'atrial fibrillation' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.602866\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coronary heart disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.603132\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'moderate coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.603519\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'heavy coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.603809\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'filtered coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.604133\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'unfiltered coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.604438\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'compound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.604826\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diterpenes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.605106\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cholesterol levels' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.605528\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'phenolic acids' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.606112\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.606545\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mendoza, mf' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.606805\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'disease' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.607115\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.607557\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diabetes mellitus' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.607986\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chemical' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.608277\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.608613\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.609059\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research method' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.609391\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'meta-analysis' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.609824\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.610075\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.610400\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura torres-collado' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.610752\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura maría compañ-gabucio' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.611364\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sandra gonzález-palacios' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.611674\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'leyre notario-barandiaran' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.612050\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alejandro oncina-cánovas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.612439\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jesús vioque' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.612753\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'manuela garcía-de la hera' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.613053\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'population' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.613307\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.613542\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health behavior' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.613979\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health outcome' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.614271\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.614649\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.615112\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.615467\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.615863\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'substance' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.616172\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.616559\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'decaffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.616818\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'polyphenols' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.617206\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'italian study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.617580\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'eureye-spain' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.617838\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'group' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.618337\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'participants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.618740\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health metric' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.619144\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'characteristics' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.619430\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'socio-demographic characteristics' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.619837\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular diseases' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.620181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'type of coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.620556\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'type' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.620880\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeinated coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.621259\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'all-cause mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.621587\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.621931\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.622302\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'country' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.622561\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spain' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.622935\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'finding' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.623231\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'preventative effects' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.623547\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study limitations' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.623825\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research conclusions' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.624271\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'demographic' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.624617\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spanish population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.625004\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'italian population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.625465\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'elderly population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.625711\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'united states of america' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.625993\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'food frequency questionnaire' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.626268\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'meta-analysis' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:23:59.626577\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean diet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\u001b[92m20:24:00 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:02 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:03 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:03 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:04.634561\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:04 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:10.329954\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:24:11 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:15 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.613402\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.613880\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.614195\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.614471\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.614721\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.614935\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:15.615182\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `ba0e59ba-8966-58b2-8dbe-0d3d5009b268`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\u001b[92m20:24:15 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:16 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:17 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:19 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:19 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:19 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:21 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:21 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:21 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:25 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:26 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:26 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:29 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:29 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:31 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:31 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Q: What are common risk factors for Type 2 Diabetes?\n",
      "A: ['Common risk factors for Type 2 Diabetes include:\\n- Obesity (Body Mass Index ≥30 kg/m²)\\n- High waist circumference (increased risk category)\\n- Sedentary lifestyle (low physical activity)\\n- Smoking status (current smokers)\\n- Hypertension\\n- High cholesterol\\n- Poor nutrition (related to coffee consumption)\\n']\n",
      "\n",
      "Q: What preventive measures reduce the risk of Hypertension?\n",
      "A: ['Preventive measures that reduce the risk of hypertension include moderate coffee consumption, which is associated with a lower risk of developing hypertension. This effect is more pronounced in individuals who are non-smokers or fast caffeine metabolizers. Additionally, filtered coffee is recommended over boiled coffee due to its antiatherogenic properties and lower cholesterol impact.']\n",
      "\n",
      "Q: What symptoms indicate possible Cardiovascular Disease?\n",
      "A: ['Possible symptoms indicating cardiovascular disease include hypertension, heart failure, and coronary heart disease. Hypertension is characterized by persistently elevated blood pressure, heart failure is a chronic condition where the heart does not pump effectively, and coronary heart disease involves the narrowing or blockage of coronary arteries due to plaque buildup.']\n",
      "\n",
      "Q: What diseases are associated with Obesity?\n",
      "A: ['Diseases associated with obesity include hypertension, cardiovascular diseases, diabetes mellitus, and coronary heart disease.']\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Test questions\n",
    "questions = [\n",
    "    \"What are common risk factors for Type 2 Diabetes?\",\n",
    "    \"What preventive measures reduce the risk of Hypertension?\",\n",
    "    \"What symptoms indicate possible Cardiovascular Disease?\",\n",
    "    \"What diseases are associated with Obesity?\"\n",
    "]\n",
    "\n",
    "# Path to medical ontology\n",
    "ontology_path = \"examples/python/ontology_input_example/enriched_medical_ontology_with_classes.owl\"  # Update with your ontology path\n",
    "\n",
    "# Run with ontology\n",
    "print(\"\\n--- Results WITH ontology ---\\n\")\n",
    "await run_pipeline(ontology_path=ontology_path)\n",
    "answers_with = await query_pipeline(questions)\n",
    "for q, a in zip(questions, answers_with):\n",
    "    print(f\"Q: {q}\\nA: {a}\\n\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "3aa18f4cdd5ceff6",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T14:32:24.891560Z",
     "start_time": "2025-04-09T14:30:47.863808Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:24:33.294076\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCleared all data from graph while preserving structure\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.317640\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mDatabase deleted successfully.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.387322\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `0693bdfd-667e-5f24-adf4-81dc64b99cb4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.387792\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.388288\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "--- Results WITHOUT ontology ---\n",
      "\n",
      "User 2da365d6-bd7c-4750-807e-74e1f340d5d2 has registered.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:24:33.505418\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `ingest_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.505934\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `resolve_data_directories`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.506308\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `0693bdfd-667e-5f24-adf4-81dc64b99cb4`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.507654\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mOntology file 'None' not found. No owl ontology will be attached to the graph.\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.515544\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run started: `63d064a5-2884-5c10-9aeb-38e16d5955ea`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.515829\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.516136\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.519493\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task started: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:33.807889\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:33 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:42 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:42 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:43 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:43 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:46 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:46 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:52 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:52 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:24:53 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.860301\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.860877\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura torres-collado' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.861358\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'laura maría compañ-gabucio' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.861788\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sandra gonzález-palacios' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.862152\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'leyre notario-barandiaran' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.862506\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'alejandro oncina-cánovas' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.863046\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'jesús vioque' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.863451\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'manuela garcía-de la hera' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.863846\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'publication' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.864353\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'nutrients 2021, 13, 1241' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.864711\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.865097\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'valencia nutrition study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.865618\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diet' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.866079\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean diet' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.866514\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.866917\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.867358\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.867809\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'location' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.868166\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'spain' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.868517\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'behavior' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.868864\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.869274\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chemical compound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.869552\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'polyphenols' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.869921\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'methodology' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.870436\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'food frequency questionnaire' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.870776\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'statistical method' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.871113\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cox regression models' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.871473\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health outcome' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.871982\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.872297\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research method' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.872635\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'meta-analysis' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.873071\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health effect' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.873456\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidant effects' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.874002\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'eureye-spain study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.874312\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'health metric' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.874779\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'population group' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.875212\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee drinkers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.875646\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'non-drinkers' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.876161\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'participants aged 20 years and above' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.876497\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diabetes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.876881\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'high cholesterol' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.877307\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'hypertension' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.877800\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'lifestyle factor' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.878190\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'physical activity' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.878605\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'tv watching' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.878979\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sleeping time' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.879320\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'study period' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.879653\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'follow-up at 6 years' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.880007\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'follow-up at 12 years' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.880342\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'follow-up at 18 years' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.880661\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'outcome' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.880998\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'metric' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.881318\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'person-years' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.881737\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.882254\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coffee consumption study' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.882621\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'population' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.882883\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mediterranean population' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.883190\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'compound' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.883511\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.883793\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'chlorogenic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.884277\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cancer mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.884620\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'all-cause mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.884959\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cvd mortality' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.885307\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'antioxidants' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.885930\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'research study' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.886296\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'torres-collado et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.886622\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'navarro et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.886932\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ruggiero et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.887227\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'quiles and vioque' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.887549\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'buckland et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.887947\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trichopoulou et al. (1995)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.888222\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'trichopoulou et al. (2003)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.888545\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'database' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.888882\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'usda national nutrient database' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.889179\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'malerba et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.889405\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'je and giovannucci' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.889677\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'grosso et al. (2016)' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.889996\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'park et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.890306\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gunter et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.890656\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'sado et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.891071\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'dinu et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.891431\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'happonen et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.891718\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'yu et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.892014\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gonzalez de mejia' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.892288\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'yamagata' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.892659\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'gökcen and sanlier' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.892965\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'machado-fragua et al.' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.893368\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'michael f. mendoza' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.893684\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'ralf martz sulague' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.893939\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'therese posas-mendoza' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.894181\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'carl j. lavie' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.894540\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'concept' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.894764\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'cardiovascular health' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.895186\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'heart failure' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.895586\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'atrial fibrillation' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.895927\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coronary heart disease' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.896211\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diterpenes' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.896419\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'filtered coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.896655\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'unfiltered coffee' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.897059\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'phenolic acid' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.897302\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'caffeine metabolism' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.897520\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'date' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.897771\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for '2023' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.898104\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'mendoza, mf' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.898394\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'condition' in category 'classes'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.898686\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'diabetes mellitus' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:53.898918\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mNo close match found for 'coronary artery risk development in young adults study 2020' in category 'individuals'\u001b[0m [\u001b[0m\u001b[1m\u001b[34mOntologyAdapter\u001b[0m]\u001b[0m\u001b[92m20:24:55 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:56 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:57 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:57 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
      "\u001b[2m2025-06-18T18:24:58.280117\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:24:58 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:25:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:01 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:02 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:02 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:05 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:06 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:06.543776\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task started: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\u001b[92m20:25:07 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:08 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:09 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:10 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:11 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.120408\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `add_data_points`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.120848\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `summarize_text`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.121088\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `extract_graph_from_data`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.121357\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mAsync Generator task completed: `extract_chunks_from_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.121589\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `check_permissions_on_dataset`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.121840\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mCoroutine task completed: `classify_documents`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks_base\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:12.122082\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mPipeline run completed: `63d064a5-2884-5c10-9aeb-38e16d5955ea`\u001b[0m [\u001b[0m\u001b[1m\u001b[34mrun_tasks(tasks: [Task], data)\u001b[0m]\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:12 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:13 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:14 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:15 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:15 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:17 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:18 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:19 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:20 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:20 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:25:22 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:22 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:23 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:24 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:24 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:25:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:27 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/text-embedding-3-large\n",
      "\u001b[1mselected model name for cost calculation: openai/text-embedding-3-large\u001b[0m\u001b[92m20:25:28 - LiteLLM:INFO\u001b[0m: utils.py:3101 - \n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\n",
      "\u001b[1m\n",
      "LiteLLM completion() model= gpt-5-mini; provider = openai\u001b[0m\u001b[92m20:25:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m\u001b[92m20:25:30 - LiteLLM:INFO\u001b[0m: cost_calculator.py:655 - selected model name for cost calculation: openai/gpt-5-mini-2024-07-18\n",
      "\u001b[1mselected model name for cost calculation: openai/gpt-5-mini-2024-07-18\u001b[0m"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Q: What are common risk factors for Type 2 Diabetes?\n",
      "A: ['Common risk factors for Type 2 Diabetes include:\\n1. Obesity (high body mass index)\\n2. High cholesterol levels\\n3. Sedentary lifestyle (low physical activity)\\n4. Poor diet choices, particularly low adherence to healthy diets like the Mediterranean diet\\n5. Age (usually occurs in adults)\\n6. Family history of diabetes\\n7. Smoking and alcohol consumption.']\n",
      "\n",
      "Q: What preventive measures reduce the risk of Hypertension?\n",
      "A: ['Preventive measures to reduce the risk of hypertension include moderate coffee consumption, which is linked to lower hypertension, improved cardiovascular health, and reduced incidence of atrial fibrillation. Additionally, antioxidants found in foods can also have protective effects.']\n",
      "\n",
      "Q: What symptoms indicate possible Cardiovascular Disease?\n",
      "A: ['Possible symptoms that may indicate cardiovascular disease include hypertension (consistently elevated blood pressure) and heart failure (a chronic condition in which the heart does not pump blood as well as it should). Additionally, high cholesterol is a health condition associated with an increased risk of cardiovascular disease.']\n",
      "\n",
      "Q: What diseases are associated with Obesity?\n",
      "A: ['Diseases associated with obesity include hypertension, diabetes mellitus, heart failure, high cholesterol, and cardiovascular disease.']\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Run without ontology\n",
    "print(\"\\n--- Results WITHOUT ontology ---\\n\")\n",
    "await run_pipeline()\n",
    "answers_without = await query_pipeline(questions)\n",
    "for q, a in zip(questions, answers_without):\n",
    "    print(f\"Q: {q}\\nA: {a}\\n\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c60533d2423acdb0",
   "metadata": {},
   "source": [
    "## Visualizing the Knowledge Graph\n",
    "\n",
    "Let's visualize how our ontology connects different medical concepts:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "36ee2a360f47a054",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-04-09T15:25:33.512697Z",
     "start_time": "2025-04-09T15:25:33.471854Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n",
      "\u001b[2m2025-06-18T18:25:30.641928\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mGraph visualization saved as /Users/borisarzentar/graph_visualization.html\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m\n",
      "\u001b[2m2025-06-18T18:25:30.642469\u001b[0m [\u001b[32m\u001b[1minfo     \u001b[0m] \u001b[1mThe HTML file has been stored on your home directory! Navigate there with cd ~\u001b[0m [\u001b[0m\u001b[1m\u001b[34mcognee.shared.logging_utils\u001b[0m]\u001b[0m"
     ]
    },
    {
     "data": {
      "text/plain": [
       "'\\n    <!DOCTYPE html>\\n    <html>\\n    <head>\\n        <meta charset=\"utf-8\">\\n        <script src=\"https://d3js.org/d3.v5.min.js\"></script>\\n        <style>\\n            body, html { margin: 0; padding: 0; width: 100%; height: 100%; overflow: hidden; background: linear-gradient(90deg, #101010, #1a1a2e); color: white; font-family: \\'Inter\\', sans-serif; }\\n\\n            svg { width: 100vw; height: 100vh; display: block; }\\n            .links line { stroke: rgba(255, 255, 255, 0.4); stroke-width: 2px; }\\n            .nodes circle { stroke: white; stroke-width: 0.5px; filter: drop-shadow(0 0 5px rgba(255,255,255,0.3)); }\\n            .node-label { font-size: 5px; font-weight: bold; fill: white; text-anchor: middle; dominant-baseline: middle; font-family: \\'Inter\\', sans-serif; pointer-events: none; }\\n            .edge-label { font-size: 3px; fill: rgba(255, 255, 255, 0.7); text-anchor: middle; dominant-baseline: middle; font-family: \\'Inter\\', sans-serif; pointer-events: none; }\\n        </style>\\n    </head>\\n    <body>\\n        <svg></svg>\\n        <script>\\n            var nodes = [{\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"nutrients\\\\nArticle\\\\nCoffee Consumption and All-Cause, Cardiovascular, and\\\\nCancer Mortality in an Adult Mediterranean Population\\\\nLaura Torres-Collado 1,2,3\\\\n , Laura Mar\\\\u00eda Compa\\\\u00f1-Gabucio 1,2,3\\\\n , Sandra Gonz\\\\u00e1lez-Palacios 1,2,3\\\\n ,\\\\nLeyre Notario-Barandiaran 1,2,3 , Alejandro Oncina-C\\\\u00e1novas 1,2,3\\\\n , Jes\\\\u00fas Vioque 1,2,3, *\\\\nand Manuela Garc\\\\u00eda-de la Hera 1,2,3\\\\n/gid00030/gid00035/gid00032/gid00030/gid00038/gid00001/gid00033/gid00042/gid00045/gid00001\\\\n/gid00048/gid00043/gid00031/gid00028/gid00047/gid00032/gid00046\\\\nCitation: Torres-Collado, L.;\\\\nCompa\\\\u00f1-Gabucio, L.M.;\\\\nGonz\\\\u00e1lez-Palacios, S.;\\\\nNotario-Barandiaran, L.;\\\\nOncina-C\\\\u00e1novas, A.; Vioque, J.;\\\\nGarc\\\\u00eda-de la Hera, M. Coffee\\\\nConsumption and All-Cause,\\\\nCardiovascular, and Cancer Mortality\\\\nin an Adult Mediterranean\\\\nPopulation. Nutrients 2021, 13, 1241.\\\\nhttps://doi.org/10.3390/nu13041241\\\\nAcademic Editor: Stefano Realdon\\\\nReceived: 17 March 2021\\\\nAccepted: 7 April 2021\\\\nPublished: 9 April 2021\\\\nPublisher\\\\u2019s Note:MDPI stays neutral\\\\nwith regard to jurisdictional claims in\\\\npublished maps and institutional af\\\\ufb01l-\\\\niations.\\\\nCopyright: \\\\u00a9 2021 by the authors.\\\\nLicensee MDPI, Basel, Switzerland.\\\\nThis article is an open access article\\\\ndistributed under the terms and\\\\nconditions of the Creative Commons\\\\nAttribution (CC BY) license (https://\\\\ncreativecommons.org/licenses/by/\\\\n4.0/).\\\\n1 Instituto de Investigaci\\\\u00f3n Sanitaria y Biom\\\\u00e9dica de Alicante, ISABIAL-UMH, 03010 Alicante, Spain;\\\\nl.torres@umh.es (L.T.-C.); lcompan@umh.es (L.M.C.-G.); sandra.gonzalezp@umh.es (S.G.-P .);\\\\nlnotario@umh.es (L.N.-B.); aoncina@umh.es (A.O.-C.); manoli@umh.es (M.G.-d.l.H.)\\\\n2 Unidad de Epidemiolog\\\\u00eda de la Nutrici\\\\u00f3n, Departamento de Salud P\\\\u00fablica, Historia de la Ciencia y\\\\nGinecolog\\\\u00eda, Universidad Miguel Hern\\\\u00e1ndez (UMH), 03550 Alicante, Spain\\\\n3 CIBER Epidemiolog\\\\u00eda y Salud P\\\\u00fablica (CIBERESP), Instituto de Salud Carlos III, 28034 Madrid, Spain\\\\n* Correspondence: vioque@umh.es; Tel.: +34-965-919-517\\\\nAbstract: We assessed the association between usual coffee consumption and all-cause, cardiovascu-\\\\nlar (CV), and cancer mortality in an adult population in Spain, taking into account both the amount\\\\nand type of coffee consumed. We used baseline data on coffee consumption and other personal\\\\nvariables, and the number of deaths during an 18-year follow-up period, for 1567 participants aged\\\\n20 years and older from the Valencia Nutrition Study in Spain. Total, caffeinated, and decaffeinated\\\\ncoffee consumption was assessed using a validated food frequency questionnaire. Cox regression\\\\nmodels were used to estimate adjusted hazard ratios (HRs) and 95% con\\\\ufb01dence intervals (CIs).\\\\nDuring the 18-year follow-up period, 317 died; 115 due to CV disease and 82 due to cancer. Com-\\\\npared with no-consumption, the consumption of \\\\u22641 cup per day and >1 cup per day of coffee was\\\\nassociated with a lower risk of all-cause mortality, HR = 0.73 (95% CI: 0.56\\\\u20130.97) and HR 0.56 (95% CI:\\\\n0.41\\\\u20130.77), respectively. A lower cancer mortality was observed among drinkers of more than 1 cup\\\\nper day compared with nondrinkers, HR 0.41 (95% CI 0.20\\\\u20130.86). Regarding the type of coffee, only\\\\nthe overall consumption of caffeinated coffee was associated with lower all-cause mortality at 12 and\\\\n18 years of follow-up, HR = 0.66 (95% CI:0.46\\\\u20130.94) and HR = 0.59 (95% CI: 0.44\\\\u20130.79), respectively.\\\\nIn conclusion, this study suggests that the moderate consumption of coffee, particularly caffeinated\\\\ncoffee (range 1\\\\u20136.5 cups per day), is associated with a lower all-cause and cancer mortality after\\\\na long follow-up period. No signi\\\\ufb01cant association was found between coffee consumption and\\\\nCVD mortality.\\\\nKeywords: coffee; caffeinated; decaffeinated; mortality; cardiovascular disease; cancer\\\\n1. Introduction\\\\nCoffee consumption is very prevalent worldwide and it has been associated with\\\\nlower total mortality, although the association is not fully consistent and the evidence\\\\nfrom Mediterranean countries is still scarce [1]. Coffee consumption has been associated\\\\nwith increased low-density lipoprotein (LDL-c) concentration [ 2], insulin resistance [3],\\\\nincreased blood pressure [4] and higher risk of some cardiovascular diseases (CVD) [4,5],\\\\nalthough no long-term adverse effects have been consistently found with its consumption.\\\\nMost of the recently published studies have reported inverse associations between habitual\\\\ncoffee consumption and the incidence of some diseases such as type 2 diabetes [6,7], mental\\\\nillness [8,9], cardiovascular diseases [10\\\\u201312], and cancer [10,13,14], all of which are major\\\\ncauses of mortality.\\\\nThese \\\\ufb01ndings are in agreement with the results obtained by Kim et al. [1] in a recent\\\\nmeta-analysis that included 40 studies and 3,852,651 subjects from different countries. In\\\\nNutrients 2021, 13, 1241. https://doi.org/10.3390/nu13041241 https://www.mdpi.com/journal/nutrients Nutrients 2021, 13, 1241 2 of 13\\\\nthis meta-analysis, a non-linear association between coffee consumption and mortality\\\\nfrom all causes, CVD, and cancer mortality was shown, with the lowest cancer mortality\\\\nobserved for the intake of two cups per day (RR = 0.96), the lowest CVD mortality for\\\\n2.5 cups per day (RR = 0.83), and the lowest all-cause mortality for 3.5 cups per day\\\\n(RR = 0.85), with no additional reduction or increase in mortality with increasing coffee\\\\nconsumption [1].\\\\nThe mechanisms by which coffee may reduce the risk of death are not well known,\\\\nalthough it could be due to the antioxidant and anti-in\\\\ufb02ammatory effects of some of their\\\\ncomponents [10,11]. Coffee is rich in polyphenols, a group of compounds with antiox-\\\\nidant and anti-in\\\\ufb02ammatory activity which can be divided according to their chemical\\\\nstructure into \\\\ufb02avonoids and non-\\\\ufb02avonoids [15,16]. Some meta-analyses have shown that\\\\n\\\\ufb02avonoids and some non-\\\\ufb02avonoids such as lignans with weak estrogen-like activity may\\\\nhave bene\\\\ufb01cial effects against cardiovascular disease and some cancers [15], although more\\\\nevidence on speci\\\\ufb01c compounds is still needed.\\\\nEvidence found in the few studies that have examined the role of coffee consump-\\\\ntion on all-cause, CVD, and cancer mortality in Mediterranean populations with high\\\\nlife-expectancy and healthy diets is still insuf\\\\ufb01cient. To the best of our knowledge, only\\\\ntwo studies have speci\\\\ufb01cally evaluated the association between coffee consumption and\\\\nmortality in adults in Spain [17,18], and both have shown an inverse association between\\\\ncoffee consumption and total and CVD mortality [17,18]. In addition, in a recently pub-\\\\nlished study with adults in Italy, a moderate consumption of 3\\\\u20134 cups/day of coffee was\\\\nassociated with lower risk of all-cause and CVD mortality [ 19]. Thus, we assessed the\\\\nassociation between coffee consumption and all-cause, CVD, and cancer mortality in a\\\\nrepresentative sample of an adult population in Valencia, Spain, taking into account both\\\\nthe amount and type of coffee.\\\\n2. Materials and Methods\\\\n2.1. Study Design and Population\\\\nData for this study came from Valencia Nutrition Survey (VNS) conducted in 1994.\\\\nSurvey methods have been described in detail elsewhere [ 20]. Brie\\\\ufb02y, the VNS was a\\\\nhealth, nutrition, and examination survey based on a representative sample, which en-\\\\nrolled 1811 adults in the Valencia Region aged 15 years and older (74.4% participation\\\\nrate). Participants younger than 20 years and those with no information regarding cof-\\\\nfee consumption were excluded from the present analysis. Thus, the \\\\ufb01nal analysis was\\\\nconducted with 1567 participants aged 20 years and above with complete information\\\\n(718 men, 849 women). We obtained written informed consent from all participants, and\\\\nthe Ethical Committees of the Hospital of San Juan and the Miguel Hernandez University\\\\napproved the study.\\\\n2.2. Coffee and Dietary Assessment\\\\nWe collected the dietary information using a validated semi-quantitative food fre-\\\\nquency questionnaire (FFQ). This FFQ was similar to the Willett questionnaire [21], which\\\\nwas adapted and validated in adult and elderly populations in Spain [22]. We used the FFQ\\\\nin the VNS that had 93 food items and included nine sections for the main food groups:\\\\ndairy, eggs, meat and \\\\ufb01sh, vegetables, fruits, breads and cereals, oils and fats, sweets and\\\\npastry, beverages, and processed foods. The validity and reproducibility of the FFQ has\\\\nbeen described previously [22], which showed satisfactory reproducibility and validity. We\\\\ncompared the nutrients and food intake estimates in the adult population with those from\\\\nfour one-week dietary records. The average correlation coef\\\\ufb01cients for one-year validity\\\\nand reproducibility of nutrient intakes were 0.47 and 0.40, respectively. We observed a\\\\ngood reproducibility for total coffee consumption, with a correlation coef\\\\ufb01cient of 0.60.\\\\nWe asked subjects in our study how often, on average, they had consumed a standard\\\\nportion size of each food item during the previous year. The FFQ had nine possible con-\\\\nsumption frequencies, ranging from \\\\u201cnever or less than once per month\\\\u201d to \\\\u201csix or more per Nutrients 2021, 13, 1241 3 of 13\\\\nday\\\\u201d. Two items were included to collect information about coffee consumption: one item\\\\nfor caffeinated coffee, and another item for decaffeinated coffee. We de\\\\ufb01ned a cup of coffee\\\\nusing typical sizes (50 mL for espresso, or 125\\\\u2013150 mL for instant/brewed/ground coffee)\\\\nand we calculated total coffee consumption in cups per day as the sum of decaffeinated and\\\\ncaffeinated coffee. We classi\\\\ufb01ed participants according to their total coffee consumption as\\\\nnon-drinkers, drinkers of \\\\u22641 cup/day, and drinkers of >1 cup/day.\\\\nAdherence to a Mediterranean diet (MD) was estimated for each subject using the\\\\nrelative Mediterranean diet score (rMED) [23], which is a variation of the original Mediter-\\\\nranean diet score [24,25]. Instead of using the median to score each component, in the rMED,\\\\nthe intake in grams of each component (except for alcohol) is referred to per1000 kcals/day\\\\nand divided into tertiles. We assigned values of 0, 1, and 2 to the \\\\ufb01rst, second, and third\\\\ntertiles of intake, respectively, for the six components that form the MD. The six categories\\\\nincluded fruits (including seeds and nuts), vegetables (excluding potatoes), \\\\ufb01sh, legumes,\\\\nolive oil, and cereals (including whole grain). Dairy products and total meat (including\\\\nprocessed meat) were negatively scored, probably because these components do not \\\\ufb01t\\\\nthe MD (lower scoring for the higher intakes). Owing to the assumed bene\\\\ufb01cial effects of\\\\nmoderate alcohol consumption, we calculated it as a dichotomous variable: 2 points for\\\\nmoderate consumption (5\\\\u201325 g/day for women and 10\\\\u201350 g/day for men), and 0 points for\\\\nhigher or lower consumption. Finally, the rMED score was estimated for each participant\\\\nby adding up the points of the 9 components. The scores ranged from 0\\\\u20136 points (low\\\\nadherence), 7\\\\u201310 (medium adherence), to 11\\\\u201318 points (high adherence). Nutrient values\\\\nand energy intake were obtained from food composition tables from the U.S. Department\\\\nof Agriculture [26] and other published Spanish sources [27].\\\\n2.3. Assessment of Mortality\\\\nWe checked the information on the date and cause of deaths through the National\\\\nDeath Index from the Spanish Statistical Of\\\\ufb01ce and the Mortality Registry in the Valencia\\\\nRegion during the 18-year follow-up period.\\\\nWe coded all causes of death according to version 10 of the International Classi\\\\ufb01ca-\\\\ntion of Diseases (ICD \\\\u221210). Due to the small number of deaths, we grouped deaths in\\\\nthree major categories, which included cardiovascular disease (ICD\\\\u221210: I00\\\\u2013I99), cancer\\\\n(ICD\\\\u221210 codes: C00\\\\u2013D49), and all-cause mortality. All-cause mortality category included\\\\ndeaths occurring from any cause as well as the \\\\ufb01rst two categories.\\\\n2.4. Other Variables\\\\nTrained \\\\ufb01eldworkers collected baseline information from all participants on socio-\\\\ndemographic and other lifestyles variables, including smoking habits, alcohol consumption,\\\\nhealth status, physical activity, and chronic diseases, using structured questionnaires.\\\\nThe following variables were considered in the analyses: sex (men, women), age\\\\n(in years), educational level (<primary school; \\\\u2265primary school), body mass index (BMI)\\\\nmeasured as weight in kilograms divided by the square of measured height in meters\\\\n(<25 kg/m2, 25\\\\u201330 kg/m2, \\\\u226530 kg/m2), waist circumference (healthy range: 78\\\\u201394 cm in\\\\nmen and 64\\\\u201380 cm in women; moderate risk: 94\\\\u2013102 cm in men and 80\\\\u201388 cm in women;\\\\nand increased risk: >102 cm in men and >88 cm in women) [ 28], smoking status (never,\\\\nex-smoker, current), self-reported main physical activity at leisure-time (low, moderate\\\\n\\\\u2013vigorous), total hours of TV watching per day, and total sleeping time in hours per day.\\\\nWe also collected the presence of pre-existing chronic disease at baseline, diabetes (no/yes),\\\\nhigh blood cholesterol (no/yes), and high blood pressure(no/yes). In the adult population,\\\\nprevious studies have shown that a high level of agreement has been observed between\\\\nself-reported diseases and those documented in the medical records [29,30]. Nutrients 2021, 13, 1241 4 of 13\\\\n2.5. Statistical Analysis\\\\nStatistical tests were bilateral, and signi\\\\ufb01cation was established at 0.05. We performed\\\\nthe analysis with the statistical software R.3.3.2 (R Foundation for Statistical Computing,\\\\nVienna, Austria, http://www.r-project.org, accessed on 1 April 2020)\\\\nWe classi\\\\ufb01ed participants according to their total coffee consumption as non-drinkers,\\\\ndrinkers of up to 1 cup per day (range 0.1\\\\u20131.0 cups), and drinkers of more than 1 cup per day\\\\n(range 1.1\\\\u20136.5). We also classi\\\\ufb01ed participants by the type of coffee in no coffee consump-\\\\ntion, caffeinated, or decaffeinated consumption. Descriptive analysis of socio-demographic\\\\nfactors was performed between different coffee consumption using percentages and Chi-\\\\nsquared tests to describe and compare categorical variables, and for continuous variables,\\\\nwe used means, standard deviations, and ANOVA tests.\\\\nWe estimated person-years for each participant of follow-up from the date of the\\\\ninterview at baseline to the date of death or completion of the 6-, 12- and 18-year follow-up,\\\\nwhichever came \\\\ufb01rst. We analyzed the association and risk of mortality at 6, 12 and 18 years\\\\nof follow-up (ad hoc division) and total, caffeinated, and decaffeinated coffee consumption\\\\nto explore the potential short, medium, and long-term effects of coffee, adjusting for other\\\\nvariables. We obtained hazard ratios (HRs) and 95% con\\\\ufb01dence intervals (95%CI) by Cox\\\\u2019s\\\\nproportional hazard for each category of coffee consumption in comparison to the lower\\\\ncategory (no consumption, \\\\u22641 cup/day, >1 cup/day) from all causes of mortality, CVD,\\\\nand cancer mortality.\\\\nTwo models were presented, one adjusted for age and sex, and multivariable analyses\\\\nwere performed, in which we further adjusted for several factors considered as potential\\\\nconfounders established in the literature and those variables showing p-values < 0.20 in\\\\nbivariate analysis. We adjusted by: sex, age (in years), education level (<primary school;\\\\n\\\\u2265primary school), BMI (<25 kg/m 2, 25\\\\u201330 kg/m 2, \\\\u226530 kg/m2), waist circumference\\\\n(healthy range: 78\\\\u201394 cm in men and 64\\\\u201380 cm in women; moderate risk: 94\\\\u2013102 cm in men\\\\nand 80\\\\u201388 cm in women; and increased risk: >102 cm in men and >88 cm in women) [28],\\\\nsmoking (never, ex-smoker, current), self-reported main physical activity at leisure-time\\\\n(very low, mostly sitting position; low, moderate\\\\u2013vigorous), adherence to a Mediterranean\\\\ndiet (rMED), hours of TV watching per day, total sleeping time in hours per day, and\\\\ndiabetes (no/yes), high blood cholesterol (no/yes), and high blood pressure (no/yes).\\\\nThe non-zero slope of the scaled Schoenfeld residuals on the time function suggested\\\\nthat the proportional hazard assumption was met. We calculated the likelihood ratio test\\\\n(LRT) to estimate the overall signi\\\\ufb01cance of coffee consumption as a categorical variable,\\\\nand we calculated trend tests to evaluate the dose\\\\u2013response for total coffee consumption as\\\\na continuous term.\\\\n3. Results\\\\nThe main characteristics of the study population according to coffee consumption\\\\nare shown in Table 1. Of 1567 participants, 78% were coffee drinkers, of whom 37.7%\\\\nwere drinkers of up to 1 cup per day, and 40.3% reported drinking more than one cup of\\\\ncoffee per day. In general, participants who consumed >1 cup/daily were more likely to be\\\\ncurrent smokers, have a higher education, spend less time watching television, and have a\\\\nlower prevalence of self-reported diabetes and hypertension.\", \"chunk_size\": 6742, \"chunk_index\": 0, \"cut_type\": \"sentence_end\", \"id\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"color\": \"#801212\"}, {\"name\": \"cardiovascular disease\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Health condition studied in relation to coffee consumption.\", \"id\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"color\": \"#f47710\"}, {\"name\": \"health condition\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"health condition\", \"id\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"color\": \"#6510f4\"}, {\"name\": \"mortality\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Outcome measure in the study assessing death rates.\", \"id\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"color\": \"#f47710\"}, {\"name\": \"health outcome\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"health outcome\", \"id\": \"c5472471-fc1f-5934-b56a-40806cdb1dfd\", \"color\": \"#6510f4\"}, {\"name\": \"mediterranean diet\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Dietary pattern followed by the study population.\", \"id\": \"73686bd4-8bf6-539f-bfb6-7005fa5cf8c1\", \"color\": \"#f47710\"}, {\"name\": \"diet\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"diet\", \"id\": \"02cad045-645c-5a93-98f5-17d79b3549dc\", \"color\": \"#6510f4\"}, {\"name\": \"laura torres-collado\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author of the study on coffee consumption and mortality.\", \"id\": \"426b61ad-65cd-5d67-8cab-afcc8c6d098f\", \"color\": \"#f47710\"}, {\"name\": \"person\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"person\", \"id\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"color\": \"#6510f4\"}, {\"name\": \"spain\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Country where the study took place.\", \"id\": \"06ac33ad-00d4-5de5-b27a-8569e42be8a7\", \"color\": \"#f47710\"}, {\"name\": \"location\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"location\", \"id\": \"19dd7d4d-a966-5ed5-82a0-6ae377761a29\", \"color\": \"#6510f4\"}, {\"name\": \"cancer\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Health condition studied in relation to coffee consumption.\", \"id\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"color\": \"#f47710\"}, {\"name\": \"polyphenols\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Group of compounds in coffee with potential health benefits.\", \"id\": \"ad852bf1-e0a7-5eed-9f7a-1fff2ba66712\", \"color\": \"#f47710\"}, {\"name\": \"chemical compound\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"chemical compound\", \"id\": \"4fb3e11c-e7e6-522b-a299-500cdd695731\", \"color\": \"#6510f4\"}, {\"name\": \"food frequency questionnaire\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Tool used to assess dietary habits in the study.\", \"id\": \"d9df2414-2628-5d0c-b448-aa2fcdd573e1\", \"color\": \"#f47710\"}, {\"name\": \"methodology\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"methodology\", \"id\": \"2424d934-8e73-5ce0-95d4-29f9cd4dfa28\", \"color\": \"#6510f4\"}, {\"name\": \"manuela garc\\\\u00eda-de la hera\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author of the study on coffee consumption and mortality.\", \"id\": \"4c8196cb-690c-596a-b1d2-190773bcfc0d\", \"color\": \"#f47710\"}, {\"name\": \"sandra gonz\\\\u00e1lez-palacios\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author of the study on coffee consumption and mortality.\", \"id\": \"03d5df54-a749-5694-931b-20d6c69fac62\", \"color\": \"#f47710\"}, {\"name\": \"laura mar\\\\u00eda compa\\\\u00f1-gabucio\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author of the study on coffee consumption and mortality.\", \"id\": \"5de4513d-9a64-58e9-b4ea-d68796890340\", \"color\": \"#f47710\"}, {\"name\": \"nutrients 2021, 13, 1241\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Academic article assessing the association between coffee consumption and mortality.\", \"id\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"color\": \"#f47710\"}, {\"name\": \"publication\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"publication\", \"id\": \"3c4c0ff9-f8fb-58ca-945c-6fc820ee0c0d\", \"color\": \"#6510f4\"}, {\"name\": \"coffee consumption\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Consumption of coffee assessed in relation to mortality.\", \"id\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"color\": \"#f47710\"}, {\"name\": \"behavior\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"behavior\", \"id\": \"15209a1f-a093-561d-a5bb-47e12a94b836\", \"color\": \"#6510f4\"}, {\"name\": \"nutrients-13-01241\", \"type\": \"PdfDocument\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"raw_data_location\": \"/Users/borisarzentar/Projects/Topoteretes/cognee/examples/data/scientific_papers/nutrients-13-01241.pdf\", \"external_metadata\": \"{}\", \"mime_type\": \"application/pdf\", \"id\": \"37e4fcd4-801c-5748-9088-125fe43fa22e\", \"color\": \"#D3D3D3\"}, {\"name\": \"valencia nutrition study\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study from which the data was collected for assessing coffee consumption.\", \"id\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"color\": \"#f47710\"}, {\"name\": \"study\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"study\", \"id\": \"96c859b6-e408-58e5-9be8-92bb84908325\", \"color\": \"#6510f4\"}, {\"name\": \"antioxidant effects\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Proposed beneficial effect of compounds in coffee.\", \"id\": \"03cd983d-6f20-5db8-9a09-0bb9b986753d\", \"color\": \"#f47710\"}, {\"name\": \"health effect\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"health effect\", \"id\": \"732c9c8b-0d81-5f38-9e7c-a8b7a6ebc692\", \"color\": \"#6510f4\"}, {\"name\": \"leyre notario-barandiaran\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author of the study on coffee consumption and mortality.\", \"id\": \"99108d40-2e45-51f8-bda7-724b8a85a88d\", \"color\": \"#f47710\"}, {\"name\": \"cox regression models\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Statistical method used to estimate hazard ratios in the study.\", \"id\": \"d4b3865e-b1ee-5600-b850-09fd81f3417c\", \"color\": \"#f47710\"}, {\"name\": \"statistical method\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"statistical method\", \"id\": \"8a61bd85-0186-59fb-8d5d-571ad63e34a0\", \"color\": \"#6510f4\"}, {\"name\": \"alejandro oncina-c\\\\u00e1novas\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author of the study on coffee consumption and mortality.\", \"id\": \"6db389ac-54c5-5955-95c7-fa3adc77efcb\", \"color\": \"#f47710\"}, {\"name\": \"jes\\\\u00fas vioque\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Co-author and corresponding author of the study on coffee consumption and mortality.\", \"id\": \"ebd7537b-8a59-57dc-8908-d7bc7d092f25\", \"color\": \"#f47710\"}, {\"name\": \"meta-analysis\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Method that aggregates study results, referenced in context.\", \"id\": \"ef3f0655-d56c-59bc-a390-0a97f6c46bdd\", \"color\": \"#f47710\"}, {\"name\": \"research method\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"research method\", \"id\": \"6b51c7bc-e83c-5160-99ef-452770420a2c\", \"color\": \"#6510f4\"}, {\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Nutrients 2021, 13, 1241 5 of 13\\\\nTable 1. Socio-demographic and lifestyle characteristics according to total coffee consumption among participants aged\\\\n20 years and above of the EUREYE-Spain and the Valencia Nutrition Study in Spain (n = 1567).\\\\nCoffee Consumption\\\\nTotal No. \\\\u22641 Cup/Day >1 Cup/Day p 1\\\\nStudy, n (%) 1567 (100.0) 345 (22.0) 591 (37.7) 631 (40.3) <0.001\\\\nSex, n (%)\\\\nMen 718 (45.8) 147 (42.6) 274 (46.4) 297 (47.1)\\\\nWomen 849 (54.2) 198 (57.4) 317 (53.6) 334 (52.9) 0.39\\\\nAge, mean (SD) 45.9 (18.0) 48.6 (20.6) 46.0 (18.8) 44.4 (15.5) 0.002\\\\nEducation Level, n (%)\\\\n<Primary school 714 (45.6) 177 (51.3) 290 (49.1) 247 (39.1)\\\\n\\\\u2265Primary school 853 (54.4) 168 (48.7) 301 (50.9) 384 (60.9) <0.001\\\\nBody Mass Index kg/m2, n (%)\\\\n<25 kg/m2 650 (41.7) 139 (40.4) 254 (43.3) 257 (40.9)\\\\n25\\\\u201330 kg/m2 623 (40.0) 126 (36.6) 232 (39.5) 265 (42.2)\\\\n\\\\u226530 kg/m2 286 (18.3) 79 (23.0) 101 (17.2) 106 (16.9) 0.11\\\\nWaist circumference *,n (%)\\\\nHealthy range 582 (37.6) 122 (36.0) 222 (37.9) 238 (38.2)\\\\nModerate risk 373 (24.1) 68 (20.1) 137 (23.4) 168 (27.0)\\\\nIncreased risk 592 (38.3) 149 (44.0) 226 (38.6) 217 (34.8) 0.05\\\\nSmoking Status, n (%)\\\\nNever 775 (49.5) 223 (64.6) 308 (52.1) 244 (38.7)\\\\nEx-smoker 262 (16.7) 44 (12.8) 101 (17.1) 117 (18.5)\\\\nCurrent 550 (33.8) 78 (22.6) 182 (30.8) 270 (42.8) <0.001\\\\nDiabetes 3 (yes), n (%) 121 (7.7) 41 (11.9) 43 (7.3) 37 (5.9) 0.003\\\\nCholesterol 3 (yes), n (%) 207 (13.2) 50 (14.5) 65 (11.0) 92 (14.6) 0.13\\\\nHypertension 3 (yes), n (%) 280 (17.9) 92 (26.7) 100 (16.9) 88 (13.9) <0.001\\\\nPhysical activity at leisure time, n (%)\\\\nLow 609 (39.6) 139 (41.4) 218 (37.4) 252 (40.6)\\\\nModerate\\\\u2013vigorous 930 (60.4) 197 (58.6) 365 (62.6) 368 (59.4) 0.38\\\\nTV watching, hours/day, mean (SD) 2.5 (1.77) 2.7 (2.0) 2.5 (1.6) 2.3 (1.7) 0.03\\\\nSleeping time, hours/day, mean (SD) 7.5 (1.4) 7.5 (1.6) 7.5 (1.4) 7.4 (1.3) 0.57\\\\nrMED, mean (SD) 8.2 (2.6) 8.3 (2.6) 8.3 (2.6) 8.1 (2.6) 0.41\\\\nAbbreviations: VNS, Valencia Nutrition Survey; SD, standard deviation; BMI, body mass index; rMED, relative Mediterranean dietary\\\\nindex. 1 p-value (p) from chi-squared test (categorical variables) and ANOVA (continuous variables). * Waist circumference: healthy range\\\\n(78\\\\u201394 cm in men and 64\\\\u201380 cm in women), moderate risk (94\\\\u2013102 cm in men and 80\\\\u201388 cm in women), increased risk (>102 cm in men and\\\\n>88 cm in women). 3 Self-reported diabetes (no/yes), high cholesterol (no/yes) and hypertension (no/yes).\\\\nAs shown in Table 2, during the \\\\ufb01rst six years of follow-up (9169.4 person-years),\\\\n85 deaths occurred. Of these deaths, 31 (36.4%) were from CV diseases and 25 (29.4%)\\\\nwere due to cancer. In the 12 years of follow-up (17,693.7 person-years), we documented\\\\n216 deaths; 77 (35.6%) due to CV diseases, and 56 (25.9%) to cancer. Finally, during\\\\nthe total 18 years of follow-up (25,526.9 person-years), we documented 317 deaths; 115\\\\n(36.3%) due to CVD, and 82 (25.9%) to cancer. Curves of cumulative incidence for all-cause\\\\nmortality during the study period according to coffee consumption are shown in Figure 1.\\\\nCoffee drinkers showed lower incidence of mortality than nondrinkers in cumulative\\\\nincidence curves. Nutrients 2021, 13, 1241 6 of 13\\\\nTable 2. Associations between the level of total coffee consumption and all-cause, cardiovascular disease, and cancer\\\\nmortality among participants of the Valencia Nutrition Survey in Spain.\\\\nCoffee Consumption\\\\nNo. \\\\u22641 Cup/Day >1 Cup/Day p-Value 2 p-Trend 3\\\\nFollow-up at 6 Years\\\\nAll-cause mortality (n, %) 345 (22.0) 591 (37.7) 631 (40.3)\\\\nDeaths, n 33 37 15\\\\nPerson-years 1971.3 3450.5 3747.6\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.72 (0.45\\\\u20131.15) 0.38 (0.20\\\\u20130.72)\\\\nMultivariable 1 1.00 0.78 (0.46\\\\u20131.30) 0.44 (0.22\\\\u20130.85) 0.01 0.04\\\\nCVD (n, %) 325 (21.5) 566 (37.4) 622 (41.1)\\\\nDeaths, n 13 12 6\\\\nPerson-years 1918.8 3369.9 3713.5\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.66 (0.30\\\\u20131.46) 0.44 (0.17\\\\u20131.20)\\\\nMultivariable 1 1.00 0.76 (0.32\\\\u20131.83) 0.42 (0.14\\\\u20131.26) 0.11 0.27\\\\nCancer (n, %) 319 569 619\\\\nDeaths, n 7 15 3\\\\nPerson-years 1891.8 3371.8 3711.0\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 1.36 (0.54\\\\u20133.35) 0.34 (0.09\\\\u20131.34)\\\\nMultivariable 1 1.00 1.54 (0.58\\\\u20134.08) 0.45 (0.10\\\\u20131.90) 0.35 0.10\\\\nFollow-up at 12 Years\\\\nAll-cause mortality (n, %) 345 (22.0) 591 (37.7) 631 (40.3)\\\\nDeaths, n 70 84 62\\\\nPerson-years 3734.7 6633.5 7325.5\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.76 (0.55\\\\u20131.05) 0.70 (0.49\\\\u20131.00)\\\\nMultivariable 1 1.00 0.75 (0.53\\\\u20131.06) 0.67 (0.46\\\\u20130.98) 0.04 0.10\\\\nCVD (n, %) 302 (21.1) 530 (37.1) 596 (41.7)\\\\nDeaths, n 27 23 27\\\\nPerson-years 3475.2 6229.7 7048.4\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.62 (0.35\\\\u20131.09) 1.03 (0.59\\\\u20131.79)\\\\nMultivariable 1 1.00 0.63 (0.34\\\\u20131.19) 1.00 (0.54\\\\u20131.89) 0.99 0.23\\\\nCancer (n, %) 289 (20.5) 537 (38.2) 581 (41.3)\\\\nDeaths, n 14 30 12\\\\nPerson-years 3385.2 6268.7 6927.5\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 1.34 (0.70\\\\u20132.55) 0.70 (0.32\\\\u20131.54)\\\\nMultivariable 1 1.00 1.37 (0.69\\\\u20132.72) 0.51 (0.20\\\\u20131.27) 0.16 0.03\\\\nFollow-up at 18 Years\\\\nAll-cause mortality (n, %) 345 (22.0) 458 (37.7) 631 (40.3)\\\\nDeaths, n 107 126 84\\\\nPerson-years 5273.3 9575.5 10,678.1\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.72 (0.56\\\\u20130.94) 0.58 (0.43\\\\u20130.79)\\\\nMultivariable 1 1.00 0.73 (0.56\\\\u20130.97) 0.56 (0.41\\\\u20130.77) <0.001 0.001\\\\nCVD (n, %) 276 (20.2) 504 (36.9) 585 (42.9)\\\\nDeaths, n 38 39 38\\\\nPerson-years 4621.5 8764.2 10,242.5\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.61 (0.38\\\\u20130.96) 0.80 (0.49\\\\u20131.27)\\\\nMultivariable 1 1.00 0.66 (0.40\\\\u20131.07) 0.71 (0.41\\\\u20131.20) 0.19 0.22\\\\nCancer (n, %) 259 (19.4) 508 (38.1) 565 (42.4)\\\\nDeaths, n 21 43 18\\\\nPerson-years 4472.8 8759.7 10,027.4\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.93 (0.55\\\\u20131.58) 0.47 (0.25\\\\u20130.90)\\\\nMultivariable 1 1.00 1.01 (0.57\\\\u20131.79) 0.41 (0.20\\\\u20130.86) 0.01 0.01\\\\n1 Cox regression model adjusted for age, sex, educational level (<Primary, \\\\u2265Primary), BMI (<25, 25.0\\\\u201329.9, \\\\u226530), waist circumference\\\\n(healthy, moderate and increased risk), sleeping time (h/day), smoking status (current; past and never), self-reported diabetes (no/yes),\\\\nhigh cholesterol (no/yes), hypertension (no/yes), relative Mediterranean diet, physical activity at leisure time (low, moderate\\\\u2013high) and\\\\nTV watching (h/day). 2 p-value from the likelihood ratio test. 3 p-value from the p-trend test. Nutrients 2021, 13, 1241 7 of 13\\\\nNutrients 2021, 13, x FOR PEER REVIEW 7 of 13 \\\\n \\\\n \\\\nFigure 1. Cumulative incidence curves of death after 18 years of follow-up, according to total cof-\\\\nfee consumption for all-cause mortality in participants from the Valencia Nutritional Survey in \\\\nSpain (n = 1567). \\\\nTable 2 shows the HRs of all-cause, CVD,  and cancer mortality for coffee consump-\\\\ntion. Coffee consumption was inversely associated with all-cause mortality during the fol-\\\\nlow-up period. After six years of follow-up, compared with non-drinkers, drinkers of \\\\u22641 \\\\ncup of regular coffee had a 22% non-significan t lower risk of death, and those who con-\\\\nsumed more than one cup/day showed a 56% reduced risk of death, HR = 0.44 (95% CI: \\\\n0.22\\\\u20130.85). Similarly, at 12 years of follow-up, lower all-cause mortality was observed \\\\namong drinkers of more than one cup per day, HR = 0.67 (95% CI: 0.46\\\\u20130.98). After 18 \\\\nyears of follow-up, drinkers of up to one cup per day and those of more than one cup per \\\\nday showed a lower risk of all-cause mortality compared with non-drinkers, HR = 0.73 \\\\n(95% CI: 0.56\\\\u20130.97) and HR = 0.56 (95% CI: 0.41\\\\u20130.77), respectively, with a significant dose\\\\u2013\\\\nresponse trend (p-trend = 0.001). The number of deaths by cancer and CV diseases after 6 \\\\nand 12 years of follow-up was too low, although after 18 years of follow-up, an inverse \\\\nassociation was observed for cancer mortality among those who consumed more than one \\\\ncup per day, HR 0.41 (95%CI: 0.20\\\\u20130.86). \\\\nThe association between type of coffee consumption and mortality at 6, 12 and 18 \\\\nyears of follow-up is shown in Table 3. Compared with non-drinkers, drinkers of caffein-\\\\nated coffee at 12 and 18 years of follow-up showed lower risks of all-cause mortality; HR \\\\n= 0.66 (95% CI: 0.46\\\\u20130.94) and HR = 0.59 (95% CI: 0.44\\\\u20130.79), respectively. There was some \\\\nevidence for an inverse association between caffeinated coffee and cancer mortality at 18 \\\\nyears of follow-up (p = 0.10). No statistically significant association was observed between \\\\ndecaffeinated coffee consumption and all-caus e, CVD, or cancer mortality during the \\\\nstudy period. \\\\nTable 3. Associations between type of coffee consumption and all-cause, cardiovascular disease, and cancer mortality \\\\namong participants of the Valencia Nutrition Survey in Spain. \\\\nCoffee Consumption \\\\n No. Decaffeinated Coffee 2 \\\\n(Range 0.1\\\\u20136.5 Cups/Day) \\\\nCaffeinated Coffee 2 \\\\n(Range 0.1\\\\u20136.5 Cups/Day) p-Value 3 \\\\n Follow-up at 6 years  \\\\nAll-cause mortality (n, %) 345 (22.0) 308 (19.7) 914 (58.3)  \\\\nDeaths, n 33 24 28  \\\\nPerson-years 1971.3 1783.4 5414.7  \\\\nFigure 1. Cumulative incidence curves of death after 18 years of follow-up, according to total coffee\\\\nconsumption for all-cause mortality in participants from the Valencia Nutritional Survey in Spain\\\\n(n = 1567).\\\\nTable 2 shows the HRs of all-cause, CVD, and cancer mortality for coffee consumption.\\\\nCoffee consumption was inversely associated with all-cause mortality during the follow-up\\\\nperiod. After six years of follow-up, compared with non-drinkers, drinkers of \\\\u22641 cup of\\\\nregular coffee had a 22% non-signi\\\\ufb01cant lower risk of death, and those who consumed\\\\nmore than one cup/day showed a 56% reduced risk of death, HR = 0.44 (95% CI: 0.22\\\\u20130.85).\\\\nSimilarly, at 12 years of follow-up, lower all-cause mortality was observed among drinkers\\\\nof more than one cup per day, HR = 0.67 (95% CI: 0.46\\\\u20130.98). After 18 years of follow-up,\\\\ndrinkers of up to one cup per day and those of more than one cup per day showed a lower\\\\nrisk of all-cause mortality compared with non-drinkers, HR = 0.73 (95% CI: 0.56\\\\u20130.97)\\\\nand HR = 0.56 (95% CI: 0.41\\\\u20130.77), respectively, with a signi\\\\ufb01cant dose\\\\u2013response trend\\\\n(p-trend = 0.001). The number of deaths by cancer and CV diseases after 6 and 12 years of\\\\nfollow-up was too low, although after 18 years of follow-up, an inverse association was\\\\nobserved for cancer mortality among those who consumed more than one cup per day, HR\\\\n0.41 (95% CI: 0.20\\\\u20130.86).\\\\nThe association between type of coffee consumption and mortality at 6, 12 and 18 years\\\\nof follow-up is shown in Table 3. Compared with non-drinkers, drinkers of caffeinated\\\\ncoffee at 12 and 18 years of follow-up showed lower risks of all-cause mortality; HR = 0.66\\\\n(95% CI: 0.46\\\\u20130.94) and HR = 0.59 (95% CI: 0.44\\\\u20130.79), respectively. There was some\\\\nevidence for an inverse association between caffeinated coffee and cancer mortality at\\\\n18 years of follow-up ( p = 0.10). No statistically signi\\\\ufb01cant association was observed\\\\nbetween decaffeinated coffee consumption and all-cause, CVD, or cancer mortality during\\\\nthe study period. Nutrients 2021, 13, 1241 8 of 13\\\\nTable 3. Associations between type of coffee consumption and all-cause, cardiovascular disease, and cancer mortality\\\\namong participants of the Valencia Nutrition Survey in Spain.\\\\nCoffee Consumption\\\\nNo. Decaffeinated Coffee 2\\\\n(Range 0.1\\\\u20136.5 Cups/Day)\\\\nCaffeinated Coffee 2\\\\n(Range 0.1\\\\u20136.5 Cups/Day) p-Value 3\\\\nFollow-up at 6 years\\\\nAll-cause mortality (n, %) 345 (22.0) 308 (19.7) 914 (58.3)\\\\nDeaths, n 33 24 28\\\\nPerson-years 1971.3 1783.4 5414.7\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.61 (0.36\\\\u20131.04) 0.55 (0.33\\\\u20130.94)\\\\nMultivariable 1 1.00 0.66 (0.37\\\\u20131.18) 0.62 (0.35\\\\u20131.10) 0.20\\\\nCVD (n, %) 325 (21.5) 295 (19.5) 893 (59.0)\\\\nDeaths, n 13 11 7\\\\nPerson-years 1918.8 1741.8 5341.6\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.72 (0.32\\\\u20131.63) 0.42 (0.16\\\\u20131.08)\\\\nMultivariable 1 1.00 0.66 (0.26\\\\u20131.65) 0.55 (0.20\\\\u20131.52) 0.46\\\\nCancer (n, %) 319 (21.2) 293 (19.4) 895 (59.4)\\\\nDeaths, n 7 9 9\\\\nPerson-years 1891.8 1736.6 5346.1\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 1.03 (0.38\\\\u20132.80) 0.81 (0.38\\\\u20132.81)\\\\nMultivariable 1 1.00 1.42 (0.50\\\\u20134.09) 0.89 (0.29\\\\u20132.69) 0.65\\\\nFollow-up at 12 years\\\\nAll-cause mortality (n, %) 345 (22.0) 308 (19.7) 914 (58.3)\\\\nDeaths, n 70 65 81\\\\nPerson-years 3734.7 3361.1 10,598.0\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.81 (0.58\\\\u20131.14) 0.68 (0.49\\\\u20130.95)\\\\nMultivariable 1 1.00 0.80 (0.55\\\\u20131.15) 0.66 (0.46\\\\u20130.94) 0.08\\\\nCVD (n, %) 302 (21.1) 271 (19.0) 855 (59.9)\\\\nDeaths, n 27 28 22\\\\nPerson-years 3475.2 3112.1 10,165.9\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.92 (0.54\\\\u20131.56) 0.64 (0.35\\\\u20131.15)\\\\nMultivariable 1 1.00 0.83 (0.45\\\\u20131.51) 0.71 (0.35\\\\u20131.41) 0.60\\\\nCancer (n, %) 289 (20.5) 261 (18.6) 857 (60.9)\\\\nDeaths, n 14 18 24\\\\nPerson-years 3385.2 3029.4 10,166.8\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 1.16 (0.58\\\\u20132.35) 1.01 (0.51\\\\u20132.00)\\\\nMultivariable 1 1.00 1.24 (0.58\\\\u20132.69) 0.88 (0.41\\\\u20131.87) 0.65\\\\nFollow-up at 18 years\\\\nAll-cause mortality (n, %) 345 (22.0) 308 (19.7) 914 (58.3)\\\\nDeaths, n 107 95 115\\\\nPerson-years 5273.3 4746.4 15,507.1\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.77 (0.58\\\\u20131.01) 0.59 (0.45\\\\u20130.77)\\\\nMultivariable 1 1.00 0.76 (0.56\\\\u20131.03) 0.59 (0.44\\\\u20130.79) 0.002\\\\nCVD (n, %) 276 (20.2) 255 (18.7) 834 (61.1)\\\\nDeaths, n 38 42 35\\\\nPerson-years 4621.5 4255.6 14,751.1\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.80 (0.51\\\\u20131.24) 0.57 (0.35\\\\u20130.92)\\\\nMultivariable 1 1.00 0.69 (0.42\\\\u20131.14) 0.70 (0.38\\\\u20131.14) 0.23\\\\nCancer (n, %) 259 (19.4) 242 (18.2) 831 (62.4)\\\\nDeaths, n 21 29 32\\\\nPerson-years 4472.8 4113.1 14,674.085\\\\nHR (95% CI)\\\\nAge and sex adjusted 1.00 0.95 (0.54\\\\u20131.69) 0.59 (0.33\\\\u20131.03)\\\\nMultivariable 1 1.00 1.01 (0.54\\\\u20131.87) 0.57 (0.31\\\\u20131.08) 0.11\\\\nAbbreviations: HR, hazard ratio; CI, con\\\\ufb01dence interval; CVD, cardiovascular disease. 1 Cox regression model adjusted for age, sex,\\\\neducational level (<Primary, \\\\u2265Primary), BMI (<25, 25.0\\\\u201329.9, \\\\u226530), waist circumference (healthy range, moderate risk and increased risk),\\\\nsleeping time (h/day), smoking status (current; past and never), self-reported diabetes (no/yes), high cholesterol (no/yes), hypertension\\\\n(no/yes), relative Mediterranean diet, physical activity at leisure time (low, moderate\\\\u2013high) and TV watching (h/day). 2 Any coffee\\\\nconsumption. 3 p-value from the likelihood ratio test.\", \"chunk_size\": 7288, \"chunk_index\": 1, \"cut_type\": \"sentence_end\", \"id\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"color\": \"#801212\"}, {\"name\": \"hypertension\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Consistently elevated blood pressure.\", \"id\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"color\": \"#f47710\"}, {\"name\": \"high cholesterol\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A condition characterized by high levels of cholesterol in the blood.\", \"id\": \"c175a217-f973-5aec-b59e-bdca26ea1a26\", \"color\": \"#f47710\"}, {\"name\": \"eureye-spain study\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A study assessing socio-demographic and lifestyle characteristics in participants aged 20 years and above in Spain.\", \"id\": \"8a95b2c3-8766-5f2b-944c-30a022abaa94\", \"color\": \"#f47710\"}, {\"name\": \"tv watching\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Average hours spent watching television per day.\", \"id\": \"c1b07b09-a33a-5b9f-9230-3011993c5d90\", \"color\": \"#f47710\"}, {\"name\": \"lifestyle factor\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"lifestyle factor\", \"id\": \"536be56d-a2ef-5caa-8b42-489997d9d5c8\", \"color\": \"#6510f4\"}, {\"name\": \"physical activity\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Level of exercise and physical activity among participants.\", \"id\": \"c0b30b48-9adb-5ce2-97bc-adceb40cc5c0\", \"color\": \"#f47710\"}, {\"name\": \"follow-up at 6 years\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Initial follow-up period of the study lasting six years.\", \"id\": \"589cdc37-861f-56ae-8499-33164a1d142c\", \"color\": \"#f47710\"}, {\"name\": \"study period\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"study period\", \"id\": \"262b23f9-b2a1-55c9-bbe7-2d48f3e7cff9\", \"color\": \"#6510f4\"}, {\"name\": \"follow-up at 12 years\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Mid follow-up period of the study lasting twelve years.\", \"id\": \"229aca40-804f-5471-81d3-39872da5cec1\", \"color\": \"#f47710\"}, {\"name\": \"non-drinkers\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Participants not consuming coffee.\", \"id\": \"83776331-108c-59f1-be51-d91819f62bf9\", \"color\": \"#f47710\"}, {\"name\": \"population group\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"population group\", \"id\": \"71ae3ac4-8c4d-5f66-a7fb-46360085350d\", \"color\": \"#6510f4\"}, {\"name\": \"participants aged 20 years and above\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Subset of participants in studies focused on individuals aged 20 and older.\", \"id\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"color\": \"#f47710\"}, {\"name\": \"sleeping time\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Average hours spent sleeping per day.\", \"id\": \"96307440-5e1f-5d23-a099-8125588c67db\", \"color\": \"#f47710\"}, {\"name\": \"diabetes\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A chronic condition that occurs when the body cannot effectively use insulin.\", \"id\": \"5e3edbad-ec37-540b-b21b-63ab4a42c952\", \"color\": \"#f47710\"}, {\"name\": \"follow-up at 18 years\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Final follow-up period of the study lasting eighteen years.\", \"id\": \"12e8cf69-b899-5748-b19d-32763c395a0b\", \"color\": \"#f47710\"}, {\"name\": \"coffee drinkers\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Participants consuming coffee.\", \"id\": \"4fc5509c-8300-53d5-b266-186fc6027de6\", \"color\": \"#f47710\"}, {\"name\": \"person-years\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A measurement of the number of years lived by participants in the study.\", \"id\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"color\": \"#f47710\"}, {\"name\": \"metric\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"metric\", \"id\": \"f45cdf53-a433-54a4-8122-7f90d2cdd32e\", \"color\": \"#6510f4\"}, {\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Nutrients 2021, 13, 1241 9 of 13\\\\n4. Discussion\\\\nIn this study, we have shown an inverse association between baseline coffee consump-\\\\ntion and all-cause and cancer mortality in an adult Mediterranean population after 18 years\\\\nof follow-up. Compared with no-consumption, coffee consumption of one or fewer cups\\\\nper day was associated with a 27% reduction in all-cause mortality, and the consumption\\\\nof more than one cup/day (range 2\\\\u20136.5 cups/day) was associated with a 44% reduction\\\\nin all-cause mortality. The consumption of more than one cup of coffee per day was also\\\\nassociated with a 59% reduction in cancer mortality after 18 years of follow-up. We did not\\\\nobserve this protective effect for CVD mortality. Regarding the type of coffee, the protective\\\\neffect was observed only between caffeinated coffee and all causes of mortality after 12 and\\\\n18 years of follow-up.\\\\nThe inverse association between coffee consumption and all-cause mortality observed\\\\nin our study is consistent with the results from previous meta-analyses in adult popula-\\\\ntions [11,31\\\\u201334], and also with results observed in subsequent prospective studies carried\\\\nout in the United States [12,35], Europe [36,37], and Asia [38]. Nevertheless, this association\\\\nhas scarcely been evaluated in adult populations from Mediterranean countries, where\\\\nthe high adherence to a Mediterranean dietary pattern may reduce mortality from all\\\\ncauses [39]. Although our results may not seem fully innovative with respect to other\\\\nstudies that have previously reported a protective effect of coffee consumption, the interest\\\\nand the novelty of this study may still be sustained by the fact that it is the \\\\ufb01rst study\\\\nto evaluate the association between coffee consumption and all-cause, CVD, and cancer\\\\nmortality in adults aged 20 years and older of a Mediterranean country, i.e., Spain. As far\\\\nas we know, only three studies have speci\\\\ufb01cally explored the association between coffee\\\\nconsumption and total mortality with Mediterranean populations. In one previous study\\\\ncarried out by our group with an elderly population in Valencia, an inverse association\\\\nwas observed with CVD but not for all causes of mortality [ 17]. In the SUN study, a\\\\nprospective cohort study with university graduate participants, an inverse association was\\\\nalso observed for all-cause mortality among participants who consumed \\\\u22654 cups/day\\\\nof coffee [18]. Finally, a recently published prospective cohort study with Italian adults\\\\nreported that moderate consumption of 3\\\\u20134 cups/day of Italian-style coffee was associated\\\\nwith lower risk of all-cause and, speci\\\\ufb01cally, of CVD mortality [19].\\\\nMost studies examining the association between coffee consumption and CV diseases\\\\nhave reported inverse associations [12,17,36,37], although in some studies the association\\\\nwas non-statistically signi\\\\ufb01cant [31,40]. In this study, we have found evidence of an inverse\\\\nassociation, which is also consistent with a study we carried out in elderly population [17].\\\\nRegarding cancer mortality, the inverse association we found is consistent with previous\\\\nstudies in different populations [35,37,38], although there are some studies showing no\\\\nassociation [12,36]. Other studies have shown an inverse association with speci\\\\ufb01c types\\\\nof cancer [41,42]; however, two recently published meta-analyses provided evidence for\\\\nan inverse association with cancer mortality [1,11]. Overall, the present evidence suggests\\\\nthat moderate coffee consumption may reduce cancer mortality, as shown in our study that\\\\nthe consumption of more than one cup per day was associated with a 59% decreased risk\\\\nof cancer mortality.\\\\nWhen we explored the association by type of coffee, we found an inverse association\\\\nbetween caffeinated coffee and all-cause mortality at 12 and 18 years of follow-up. Although\\\\nsome studies show that caffeine contained in coffee may produce some adverse effects in\\\\nthe central nervous system and cardiovascular system [4,5,43], several cohort studies have\\\\nfound that moderate caffeine consumption is associated with a decreased risk of all-cause\\\\nmortality in adult populations [12,35]. Most of these studies have also reported an inverse\\\\nassociation with decaffeinated coffee consumption, which we did not observe in our study,\\\\nalthough our study had the lack of power to detect an association because the number of\\\\nevents by categories of decaffeinated coffee was small, and decaffeinated coffee was also\\\\nless frequently consumed than caffeinated coffee. Nutrients 2021, 13, 1241 10 of 13\\\\nSeveral biological mechanisms have been proposed to explain why coffee may de-\\\\ncrease the risk of mortality. Coffee is a rich source of antioxidant components such as\\\\ncaffeine, chlorogenic acid, melanoidins, cafestol, kahweol, and trigonelline, as well as other\\\\npolyphenol compounds that may have important bene\\\\ufb01cial effects on in\\\\ufb02ammation, and\\\\nbene\\\\ufb01cial effects have been shown against total mortality, cardiovascular disease and some\\\\ncancers [15]. Firstly, caffeine and chlorogenic acid contents in coffee produce an inhibition\\\\nof peroxidation of LDL-c which prevents the development of atherosclerosis and decreases\\\\noxidative stress, preventing endothelial dysfunction [44,45]. Moreover, other phenolic com-\\\\npounds and substances such as trigonelline or magnesium may improve insulin sensitivity\\\\nand glucose resistance [7]. Finally, coffee may produce biological anticarcinogenic effects,\\\\nincluding inhibition of the enzyme responsible for carcinogen activation, the stimulation\\\\nof intracellular antioxidant defense mechanisms, and inhibition of DNA methylation that\\\\nmanages the inactivation of tumorigenic process and apoptosis [45]. Thus, compounds of\\\\ncoffee might play a bene\\\\ufb01cial role in health, mediating not only the association between\\\\nlong-term coffee consumption and risk of all-cause mortality, but also with cancer mortality.\\\\nThe current study has several limitations. Firstly, we were not able to control for possi-\\\\nble changes in coffee consumption during the follow-up; however, coffee consumption is a\\\\nhabit adopted in adult life that rarely changes over time, and the self-reported consumption\\\\ncould be a valid method to assess usual long-term coffee consumption [12,46]. Secondly,\\\\nit is possible that pre-existing chronic illness at baseline might cause higher mortality\\\\nand be also associated with lower or non-coffee consumption. When we repeated the\\\\nanalyses excluding deaths in the \\\\ufb01rst and second year of the follow-up and adjusted for the\\\\nself-reported pre-existing chronic diseases at baseline, the associations remained basically\\\\nunchanged (data not shown). Thirdly, although participants were volunteers in a nutrition\\\\nsurvey and some response bias may be possible, it is unlikely that coffee consumption\\\\nwas in\\\\ufb02uential in the participation rate in the study, and coffee consumption among our\\\\nparticipants was similar to that found in other Spanish studies [17,18]. Additionally, we\\\\ndid not collect information on the method of coffee preparation, but a previous study\\\\nshowed that un\\\\ufb01ltered coffee is the most widely consumed in Spain [47]. Lastly, a point to\\\\nconsider is the small sample size, which may have limited the statistical power to detect\\\\nsome associations as signi\\\\ufb01cant (e.g., CV diseases); however, the follow-up period was\\\\nlong enough to detect signi\\\\ufb01cant associations with all-cause and cancer mortality.\\\\nOur study has several strengths, however. We used a well-de\\\\ufb01ned population com-\\\\nprising participants aged 20 or above from a well-de\\\\ufb01ned Mediterranean area from which\\\\nhigh-quality information was collected at baseline by trained \\\\ufb01eldworkers using stan-\\\\ndardized protocols and validated questionnaires. In addition, the information on coffee\\\\nconsumption was collected before the outcome occurred; thus, any misclassi\\\\ufb01cation in\\\\ncoffee consumption categories, if any, should be non-differential, and could therefore lead\\\\nto an underestimation of the effects of coffee on mortality.\\\\n5. Conclusions\\\\nIn conclusion, this study suggests that the moderate consumption of coffee, partic-\\\\nularly caffeinated coffee (range 1\\\\u20136.5 cups per day), is associated with a lower all-cause\\\\nand cancer mortality after a long follow-up period. These \\\\ufb01ndings are consistent with\\\\nprevious studies, although they add new evidence from a Mediterranean adult population.\\\\nThus, coffee consumption could be promoted as part of a healthy Mediterranean lifestyle,\\\\nalthough further long-term longitudinal studies collecting information on the amount and\\\\ntype of coffee should add valuable information regarding its bene\\\\ufb01cial effects.\\\\nAuthor Contributions: Conceptualization, J.V . and M.G.-d.l.H.; formal analysis, L.T.-C.; datacuration,\\\\nL.T.-C. and J.V .; writing\\\\u2014original draft preparation, L.T.-C.; writing\\\\u2014review and editing, L.T.-C.,\\\\nL.M.C.-G., S.G.-P ., L.N.-B., and A.O.-C.; supervision, J.V . and M.G.-d.l.H. All authors have read and\\\\nagreed to the published version of the manuscript. Nutrients 2021, 13, 1241 11 of 13\\\\nFunding: The VNS study was supported by a grant from the Direcci\\\\u00f3n General de Salud P\\\\u00fablica,\\\\nGeneralitat Valenciana 1994 and the Fondo Investigacion Sanitaria (FIS 00/0985). This study has also\\\\nreceived support from the Instituto de Salud Carlos III and FEDER funds (FIS PI13/00654).\\\\nInstitutional Review Board Statement: The study was conducted according to the guidelines of the\\\\nDeclaration of Helsinki, and approved by the local Ethical Committees of the Hospital of San Juan\\\\nand the Miguel Hernandez University.\\\\nInformed Consent Statement: Informed consent was obtained from all subjects involved inthe study.\\\\nData Availability Statement: The data presented in this study are available on request from the\\\\ncorresponding author. The data are not publicly available due to con\\\\ufb01dentiality and ethical reasons.\\\\nAcknowledgments: The authors thank the VNS participants for their valuable contribution to this\\\\nresearch. We appreciate the English revision of the manuscript made by Jessica Gorlin.\\\\nCon\\\\ufb02icts of Interest: The authors declare no con\\\\ufb02ict of interest. The funders had no role in the design\\\\nof the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript, or\\\\nin the decision to publish the results.\\\\nReferences\\\\n1. Kim, Y.; Je, Y.; Giovannucci, E. Coffee Consumption and All-Cause and Cause-Speci\\\\ufb01c Mortality: A Meta-Analysis by Potential\\\\nModi\\\\ufb01ers. Eur. J. Epidemiol.2019. [CrossRef] [PubMed]\\\\n2. Cai, L.; Ma, D.; Zhang, Y.; Liu, Z.; Wang, P . The Effect of Coffee Consumption on Serum Lipids: A Meta-Analysis of Randomized\\\\nControlled Trials. Eur. J. Clin. Nutr.2012, 66, 872\\\\u2013877. [CrossRef] [PubMed]\\\\n3. Higdon, J.V .; Frei, B. Coffee and Health: A Review of Recent Human Research. Crit. Rev. Food Sci. Nutr.2006, 46, 101\\\\u2013123.\\\\n[CrossRef]\\\\n4. Palatini, P .; Fania, C.; Mos, L.; Garavelli, G.; Mazzer, A.; Cozzio, S.; Saladini, F.; Casiglia, E. Coffee Consumption and Risk of\\\\nCardiovascular Events in Hypertensive Patients. Results from the HARVEST. Int. J. Cardiol. 2016, 212, 131\\\\u2013137. [CrossRef]\\\\n[PubMed]\\\\n5. Liu, J.; Sui, X.; Lavie, C.J.; Hebert, J.R.; Earnest, C.P .; Zhang, J.; Blair, S.N. Association of Coffee Consumption with All-Cause and\\\\nCardiovascular Disease Mortality. Mayo Clin. Proc.2013, 88, 1066\\\\u20131074. [CrossRef] [PubMed]\\\\n6. Ding, M.; Bhupathiraju, S.N.; Chen, M.; van Dam, R.M.; Hu, F.B. Caffeinated and Decaffeinated Coffee Consumption and Risk of\\\\nType 2 Diabetes: A Systematic Review and a Dose-Response Meta-Analysis. Diabetes Care2014, 37, 569\\\\u2013586. [CrossRef]\\\\n7. Santos, R.M.M.; Lima, D.R.A. Coffee Consumption, Obesity and Type 2 Diabetes: A Mini-Review.Eur. J. Nutr.2016, 55, 1345\\\\u20131358.\\\\n[CrossRef]\\\\n8. Wu, L.; Sun, D.; He, Y. Coffee Intake and the Incident Risk of Cognitive Disorders: A Dose-Response Meta-Analysis of Nine\\\\nProspective Cohort Studies. Clin. Nutr.2017, 36, 730\\\\u2013736. [CrossRef]\\\\n9. Liu, Q.-P .; Wu, Y.-F.; Cheng, H.-Y.; Xia, T.; Ding, H.; Wang, H.; Wang, Z.-M.; Xu, Y. Habitual Coffee Consumption and Risk of\\\\nCognitive Decline/Dementia: A Systematic Review and Meta-Analysis of Prospective Cohort Studies. Nutrition 2016, 32, 628\\\\u2013636.\\\\n[CrossRef] [PubMed]\\\\n10. Grosso, G.; Godos, J.; Galvano, F.; Giovannucci, E.L. Coffee, Caffeine, and Health Outcomes: An Umbrella Review.Annu. Rev.\\\\nNutr. 2017, 37, 131\\\\u2013156. [CrossRef]\\\\n11. Poole, R.; Kennedy, O.J.; Roderick, P .; Fallow\\\\ufb01eld, J.A.; Hayes, P .C.; Parkes, J. Coffee Consumption and Health: Umbrella Review\\\\nof Meta-Analyses of Multiple Health Outcomes. BMJ 2017, 359, 5024. [CrossRef] [PubMed]\\\\n12. Ding, M.; Satija, A.; Bhupathiraju, S.N.; Hu, Y.; Sun, Q.; Han, J.; Lopez-Garcia, E.; Willett, W.; Dam, R.M.v.; Hu, F.B. Association of\\\\nCoffee Consumption with Total and Cause-Speci\\\\ufb01c Mortality in Three Large Prospective Cohorts.Circulation 2015, 132, 2305\\\\u20132315.\\\\n[CrossRef]\\\\n13. Bravi, F.; Tavani, A.; Bosetti, C.; Boffetta, P .; La Vecchia, C. Coffee and the Risk of Hepatocellular Carcinoma and Chronic Liver\\\\nDisease: A Systematic Review and Meta-Analysis of Prospective Studies. Eur. J. Cancer Prev.2017, 26, 368\\\\u2013377. [CrossRef]\\\\n[PubMed]\\\\n14. Caini, S.; Cattaruzza, S.; Bendinelli, B.; Tosti, G.; Masala, G.; Gnagnarella, P .; Assedi, M.; Stanganelli, I.; Palli, D.; Gandini, S.\\\\nCoffee, Tea and Caffeine Intake and the Risk of Non-Melanoma Skin Cancer: A Review of the Literature and Meta-Analysis. Eur.\\\\nJ. Nutr.2016, 56, 1\\\\u201312. [CrossRef]\\\\n15. Grosso, G.; Micek, A.; Godos, J.; Pajak, A.; Sciacca, S.; Galvano, F.; Giovannucci, E.L. Dietary Flavonoid and Lignan Intake and\\\\nMortality in Prospective Cohort Studies: Systematic Review and Dose-Response Meta-Analysis. Am. J. Epidemiol.2017, 185,\\\\n1304\\\\u20131316. [CrossRef] [PubMed]\\\\n16. Ludwig, I.A.; Clifford, M.N.; Lean, M.E.J.; Ashihara, H.; Crozier, A. Coffee: Biochemistry and Potential Impact on Health.\\\\nFood Funct.2014, 5, 1695\\\\u20131717. [CrossRef] [PubMed]\", \"chunk_size\": 5806, \"chunk_index\": 2, \"cut_type\": \"sentence_cut\", \"id\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"color\": \"#801212\"}, {\"name\": \"cvd mortality\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Death rate from cardiovascular diseases.\", \"id\": \"9b0132a6-2fa9-50d4-9786-7856610c9e31\", \"color\": \"#f47710\"}, {\"name\": \"health metric\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"health metric\", \"id\": \"3d896feb-144d-51bd-9aeb-afe8e845a3e4\", \"color\": \"#6510f4\"}, {\"name\": \"chlorogenic acid\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A compound in coffee believed to have health benefits.\", \"id\": \"0ca0ad29-9f79-5d2c-b6b6-325df830ed1c\", \"color\": \"#f47710\"}, {\"name\": \"compound\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"compound\", \"id\": \"addbc55c-7f21-5cae-86c4-8cb0de93452b\", \"color\": \"#6510f4\"}, {\"name\": \"coffee consumption study\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A study on the association between coffee consumption and mortality rates in a Mediterranean population.\", \"id\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"color\": \"#f47710\"}, {\"name\": \"research\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"research\", \"id\": \"931754d5-ca60-5ed3-a7ea-e569447223c6\", \"color\": \"#6510f4\"}, {\"name\": \"caffeine\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A natural stimulant found in coffee, associated with health effects.\", \"id\": \"c78c1da9-aa59-509c-8764-e7988ba0d4cc\", \"color\": \"#f47710\"}, {\"name\": \"mediterranean population\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Adults from Mediterranean countries, specifically Spain.\", \"id\": \"a2c4702d-8e81-531c-8ab8-2a147b4c7cc3\", \"color\": \"#f47710\"}, {\"name\": \"population\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"population\", \"id\": \"66d00649-f9eb-5eec-ac58-b91bb0662ffd\", \"color\": \"#6510f4\"}, {\"name\": \"antioxidants\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Compounds that inhibit oxidation and may reduce health risks.\", \"id\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"color\": \"#f47710\"}, {\"name\": \"cancer mortality\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Death rate from cancer.\", \"id\": \"bd749f32-5faa-53fc-8dd0-fc1c70e9ef31\", \"color\": \"#f47710\"}, {\"name\": \"all-cause mortality\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Death rate from all causes.\", \"id\": \"b2a10138-f686-5689-b9ba-c485572a90d0\", \"color\": \"#f47710\"}, {\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Nutrients 2021, 13, 1241 12 of 13\\\\n17. Torres-Collado, L.; Garcia-de-la-Hera, M.; Navarrete-Mu\\\\u00f1oz, E.M.; Notario-Barandiaran, L.; Gonzalez-Palacios, S.; Zurriaga, O.;\\\\nMelchor, I.; Vioque, J. Coffee Consumption and Mortality from All Causes of Death, Cardiovascular Disease and Cancer in an\\\\nElderly Spanish Population. Eur. J. Nutr.2018. [CrossRef]\\\\n18. Navarro, A.M.; Martinez-Gonzalez, M.\\\\u00c1.; Gea, A.; Grosso, G.; Mart\\\\u00edn-Moreno, J.M.; Lopez-Garcia, E.; Martin-Calvo, N.; Toledo,\\\\nE. Coffee Consumption and Total Mortality in a Mediterranean Prospective Cohort. Am. J. Clin. Nutr.2018, 108, 1113\\\\u20131120.\\\\n[CrossRef]\\\\n19. Ruggiero, E.; Di Castelnuovo, A.; Costanzo, S.; Persichillo, M.; De Curtis, A.; Cerletti, C.; Donati, M.B.; de Gaetano, G.; Iacoviello,\\\\nL.; Bonaccio, M.; et al. Daily Coffee Drinking Is Associated with Lower Risks of Cardiovascular and Total Mortality in a General\\\\nItalian Population: Results from the Moli-Sani Study. J. Nutr.2021, 151, 395\\\\u2013404. [CrossRef]\\\\n20. Quiles, J.; Vioque, J. Prevalence of obesity in the Valencian community. Med. Clin.1998, 110, 319.\\\\n21. Willett, W.C.; Sampson, L.; Stampfer, M.J.; Rosner, B.; Bain, C.; Witschi, J.; Hennekens, C.H.; Speizer, F.E. Reproducibility and\\\\nValidity of a Semiquantitative Food Frequency Questionnaire. Am. J. Epidemiol.1985, 122, 51\\\\u201365. [CrossRef]\\\\n22. Vioque, J.; Gonz\\\\u00e1lez, L. Validity of a Food Frequency Questionnaire (Preliminary Results). Eur. J. Cancer Prev.1991, 1, 19\\\\u201320.\\\\n[CrossRef]\\\\n23. Buckland, G.; Gonz \\\\u00e1lez, C.A.; Agudo, A.; Vilardell, M.; Berenguer, A.; Amiano, P .; Ardanaz, E.; Arriola, L.; Barricarte, A.;\\\\nBasterretxea, M.; et al. Adherence to the Mediterranean Diet and Risk of Coronary Heart Disease in the Spanish EPIC Cohort\\\\nStudy. Am. J. Epidemiol.2009, 170, 1518\\\\u20131529. [CrossRef] [PubMed]\\\\n24. Trichopoulou, A.; Kouris-Blazos, A.; Wahlqvist, M.L.; Gnardellis, C.; Lagiou, P .; Polychronopoulos, E.; Vassilakou, T.; Lipworth,\\\\nL.; Trichopoulos, D. Diet and Overall Survival in Elderly People. BMJ 1995, 311, 1457\\\\u20131460. [CrossRef] [PubMed]\\\\n25. Trichopoulou, A.; Costacou, T.; Bamia, C.; Trichopoulos, D. Adherence to a Mediterranean Diet and Survival in a Greek Population.\\\\nN. Engl. J. Med.2003, 348, 2599\\\\u20132608. [CrossRef] [PubMed]\\\\n26. U.S. Department of Agriculture ARS; USDA Nutrient Data Laboratory. USDA National Nutrient Database for Standard Reference;\\\\nRelease 23; Washington, DC, USA, 2008.\\\\n27. Palma, I.; Farran, A.; Cant\\\\u00f3s, D. Tablas de Composici\\\\u00f3n de Alimentos Por Medidas Caseras de Consumo Habitual En Espa\\\\u00f1a. Centre\\\\nd\\\\u2019Ensenyament Superior de Nutrici\\\\u00f3 i Diet\\\\u00e9tica (CESNID); Mc Graw-Hill Interamericana: Madrid, Spain, 2008.\\\\n28. Lean, M.E.; Han, T.S.; Morrison, C.E. Waist Circumference as a Measure for Indicating Need for Weight Management.BMJ 1995,\\\\n311, 158\\\\u2013161. [CrossRef] [PubMed]\\\\n29. Bush, T.L.; Miller, S.R.; Golden, A.L.; Hale, W.E. Self-Report and Medical Record Report Agreement of Selected Medical Conditions\\\\nin the Elderly. Am. J. Public Health1989, 79, 1554\\\\u20131556. [CrossRef] [PubMed]\\\\n30. Harlow, S.D.; Linet, M.S. Agreement between Questionnaire Data and Medical Records. The Evidence for Accuracy of Recall.\\\\nAm. J. Epidemiol.1989, 129, 233\\\\u2013248. [CrossRef]\\\\n31. Malerba, S.; Turati, F.; Galeone, C.; Pelucchi, C.; Verga, F.; La Vecchia, C.; Tavani, A. A Meta-Analysis of Prospective Studies of\\\\nCoffee Consumption and Mortality for All Causes, Cancers and Cardiovascular Diseases. Eur. J. Epidemiol.2013, 28, 527\\\\u2013539.\\\\n[CrossRef] [PubMed]\\\\n32. Crippa, A.; Discacciati, A.; Larsson, S.C.; Wolk, A.; Orsini, N. Coffee Consumption and Mortality from All Causes, Cardiovascular\\\\nDisease, and Cancer: A Dose-Response Meta-Analysis. Am. J. Epidemiol.2014, 180, 763\\\\u2013775. [CrossRef]\\\\n33. Je, Y.; Giovannucci, E. Coffee Consumption and Total Mortality: A Meta-Analysis of Twenty Prospective Cohort Studies.Br. J.\\\\nNutr. 2014, 111, 1162\\\\u20131173. [CrossRef] [PubMed]\\\\n34. Grosso, G.; Micek, A.; Godos, J.; Sciacca, S.; Pajak, A.; Mart \\\\u00ednez-Gonz\\\\u00e1lez, M.A.; Giovannucci, E.L.; Galvano, F. Coffee\\\\nConsumption and Risk of All-Cause, Cardiovascular, and Cancer Mortality in Smokers and Non-Smokers: A Dose-Response\\\\nMeta-Analysis. Eur. J. Epidemiol.2016, 31, 1191\\\\u20131205. [CrossRef] [PubMed]\\\\n35. Park, S.-Y.; Freedman, N.D.; Haiman, C.A.; Le Marchand, L.; Wilkens, L.R.; Setiawan, V .W. Association of Coffee Consumption\\\\nWith Total and Cause-Speci\\\\ufb01c Mortality Among Nonwhite Populations. Ann. Intern. Med. 2017, 167, 228\\\\u2013235. [CrossRef]\\\\n[PubMed]\\\\n36. Gunter, M.J.; Murphy, N.; Cross, A.J.; Dossus, L.; Dartois, L.; Fagherazzi, G.; Kaaks, R.; K\\\\u00fchn, T.; Boeing, H.; Aleksandrova, K.;\\\\net al. Coffee Drinking and Mortality in 10 European Countries: A Multinational Cohort Study. Ann. Intern. Med. 2017, 167,\\\\n236\\\\u2013247. [CrossRef] [PubMed]\\\\n37. Grosso, G.; Stepaniak, U.; Micek, A.; Ste\\\\ufb02er, D.; Bobak, M.; Pajak, A. Coffee Consumption and Mortality in Three Eastern\\\\nEuropean Countries: Results from the HAPIEE (Health, Alcohol and Psychosocial Factors In Eastern Europe) Study. Public Health\\\\nNutr. 2016, 20, 82\\\\u201391. [CrossRef] [PubMed]\\\\n38. Sado, J.; Kitamura, T.; Kitamura, Y.; Liu, R.; Ando, E.; Sobue, T.; Sugawara, Y.; Matsuo, K.; Nakayama, T.; Tsuji, I.; et al. Coffee\\\\nConsumption and All-Cause and Cardiovascular Mortality-Three-Prefecture Cohort in Japan.Circ. J.2019, 83, 757\\\\u2013766. [CrossRef]\\\\n39. Dinu, M.; Pagliai, G.; Casini, A.; So\\\\ufb01, F. Mediterranean Diet and Multiple Health Outcomes: An Umbrella Review of Meta-\\\\nAnalyses of Observational Studies and Randomised Trials. Eur. J. Clin. Nutr.2018, 72, 30\\\\u201343. [CrossRef]\\\\n40. Happonen, P .; L\\\\u00e4\\\\u00e4r\\\\u00e4, E.; Hiltunen, L.; Luukinen, H. Coffee Consumption and Mortality in a 14-Year Follow-up of an Elderly\\\\nNorthern Finnish Population. Br. J. Nutr.2008, 99, 1354\\\\u20131361. [CrossRef]\\\\n41. Sado, J.; Kitamura, T.; Kitamura, Y.; Sobue, T.; Nishino, Y.; Tanaka, H.; Nakayama, T.; Tsuji, I.; Ito, H.; Suzuki, T.; et al. Association\\\\nbetween Coffee Consumption and All-Sites Cancer Incidence and Mortality. Cancer Sci.2017, 108, 2079\\\\u20132087. [CrossRef] Nutrients 2021, 13, 1241 13 of 13\\\\n42. Yu, X.; Bao, Z.; Zou, J.; Dong, J. Coffee Consumption and Risk of Cancers: A Meta-Analysis of Cohort Studies. BMC Cancer2011,\\\\n11, 96. [CrossRef]\\\\n43. Gonzalez de Mejia, E.; Ramirez-Mares, M.V . Impact of Caffeine and Coffee on Our Health.Trends Endocrinol. Metab.2014, 25,\\\\n489\\\\u2013492. [CrossRef] [PubMed]\\\\n44. Yamagata, K. Do Coffee Polyphenols Have a Preventive Action on Metabolic Syndrome Associated Endothelial Dysfunctions?\\\\nAn Assessment of the Current Evidence. Antioxidants 2018, 7, 26. [CrossRef] [PubMed]\\\\n45. G\\\\u00f6kcen, B.B.; \\\\u00b8 Sanlier, N. Coffee Consumption and Disease Correlations.Crit. Rev. Food Sci. Nutr.2019, 59, 336\\\\u2013348. [CrossRef]\\\\n[PubMed]\\\\n46. Penolazzi, B.; Natale, V .; Leone, L.; Russo, P .M. Individual Differences Affecting Caffeine Intake. Analysis of Consumption\\\\nBehaviours for Different Times of Day and Caffeine Sources. Appetite 2012, 58, 971\\\\u2013977. [CrossRef]\\\\n47. Machado-Fragua, M.D.; Struijk, E.A.; Graciani, A.; Guallar-Castillon, P .; Rodr\\\\u00edguez-Artalejo, F.; Lopez-Garcia, E. Coffee Con-\\\\nsumption and Risk of Physical Function Impairment, Frailty and Disability in Older Adults. Eur. J. Nutr.2019, 58, 1415\\\\u20131427.\\\\n[CrossRef] [PubMed]\", \"chunk_size\": 3671, \"chunk_index\": 3, \"cut_type\": \"sentence_cut\", \"id\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"color\": \"#801212\"}, {\"name\": \"grosso et al. (2016)\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Meta-analysis of coffee consumption and mortality in smokers and non-smokers.\", \"id\": \"3ba13355-e09c-5af5-94ba-c4c49856e595\", \"color\": \"#f47710\"}, {\"name\": \"research study\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"research study\", \"id\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"color\": \"#6510f4\"}, {\"name\": \"gonzalez de mejia\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on the impact of caffeine and coffee on health.\", \"id\": \"832d2fd5-626b-5436-a2db-af7ee6722c27\", \"color\": \"#f47710\"}, {\"name\": \"je and giovannucci\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Meta-analysis of coffee consumption and total mortality.\", \"id\": \"280404f4-d1d4-5053-afdf-aee728a4ac40\", \"color\": \"#f47710\"}, {\"name\": \"torres-collado et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and mortality in an elderly Spanish population.\", \"id\": \"86bc15f8-dde3-5a97-bffa-83b1f68a2636\", \"color\": \"#f47710\"}, {\"name\": \"gunter et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee drinking and mortality in 10 European countries.\", \"id\": \"aecdfa63-2116-580d-b26b-12b4a2fd2ab7\", \"color\": \"#f47710\"}, {\"name\": \"park et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and total and cause-specific mortality among nonwhite populations.\", \"id\": \"685dea78-218d-5b8e-9ed3-270da5257b2c\", \"color\": \"#f47710\"}, {\"name\": \"dinu et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Umbrella review of the Mediterranean diet and multiple health outcomes.\", \"id\": \"a34476ef-9d9e-5323-8d2c-b3377401be07\", \"color\": \"#f47710\"}, {\"name\": \"happonen et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and mortality in a Finnish population.\", \"id\": \"8097f2a6-d14e-5e0f-b6c5-53e8e55839b5\", \"color\": \"#f47710\"}, {\"name\": \"trichopoulou et al. (2003)\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on adherence to the Mediterranean diet and survival in a Greek population.\", \"id\": \"0119136a-8473-5b1d-9c19-231a37583250\", \"color\": \"#f47710\"}, {\"name\": \"ruggiero et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study associating daily coffee drinking with lower risks of cardiovascular disease and total mortality in an Italian population.\", \"id\": \"53f1ca8e-f701-5c29-8967-db9967174aed\", \"color\": \"#f47710\"}, {\"name\": \"navarro et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and total mortality in a Mediterranean prospective cohort.\", \"id\": \"ecdcfbf3-cadf-580c-9490-b3ad26964e9b\", \"color\": \"#f47710\"}, {\"name\": \"usda national nutrient database\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Standard reference for nutrient data by the U.S. Department of Agriculture.\", \"id\": \"1c41f80f-f723-54cb-8991-1d4913a82b73\", \"color\": \"#f47710\"}, {\"name\": \"database\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"database\", \"id\": \"90cb1fed-d3a3-51c4-bf2d-467bce3d40a3\", \"color\": \"#6510f4\"}, {\"name\": \"sado et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and all-cause and cardiovascular mortality in Japan.\", \"id\": \"a106fc02-1ada-5972-a24f-6f5f23592c4f\", \"color\": \"#f47710\"}, {\"name\": \"machado-fragua et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and risk of physical function impairment in older adults.\", \"id\": \"435650bb-100e-59c2-96e4-f3d403db5f3d\", \"color\": \"#f47710\"}, {\"name\": \"malerba et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Meta-analysis of prospective studies on coffee consumption and mortality.\", \"id\": \"46a295a5-5ac7-5fb9-8f34-be9738c31358\", \"color\": \"#f47710\"}, {\"name\": \"g\\\\u00f6kcen and sanlier\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on coffee consumption and disease correlations.\", \"id\": \"eaf6ed9d-b3a5-50fe-9b53-40470f11dc3c\", \"color\": \"#f47710\"}, {\"name\": \"quiles and vioque\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on prevalence of obesity in the Valencian community.\", \"id\": \"9cae226b-7048-50c4-9162-461438c0b9f0\", \"color\": \"#f47710\"}, {\"name\": \"yu et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Meta-analysis of coffee consumption and risk of cancers.\", \"id\": \"20851b25-35e0-53b6-a2dc-46aa2b0c736b\", \"color\": \"#f47710\"}, {\"name\": \"buckland et al.\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on adherence to the Mediterranean diet and risk of coronary heart disease in the Spanish EPIC cohort.\", \"id\": \"46a52c54-a100-5e31-be75-9c91c06f9198\", \"color\": \"#f47710\"}, {\"name\": \"trichopoulou et al. (1995)\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Study on diet and overall survival in elderly people.\", \"id\": \"0fc618e7-1917-5c7c-b74e-28bf71640010\", \"color\": \"#f47710\"}, {\"name\": \"yamagata\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Assessment of coffee polyphenols\\' preventive action on metabolic syndrome.\", \"id\": \"b7d3f418-8d8c-534d-88ce-4d20046149af\", \"color\": \"#f47710\"}, {\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"REVIEWSANDCONTEMPORARYUPDATES\\\\nOchsner Journal23:152\\\\u2013158, 2023\\\\n\\\\u00a92023 by the author(s); Creative Commons Attribution License (CC BY)\\\\nDOI: 10.31486/toj.22.0073\\\\nImpact of Coffee Consumption on Cardiovascular Health\\\\nMichael F. Mendoza, MD,1 Ralf Martz Sulague, MD,2 Therese Posas-Mendoza, MD,3 Carl J. Lavie, MD4,5\\\\n1The Gayle and Tom Benson Cancer Center, Ochsner Clinic Foundation, New Orleans, LA2School of Health, Georgetown University,\\\\nWashington, DC3Department of Rheumatology, Ochsner Clinic Foundation, Covington, LA4Department of Cardiology, Ochsner Clinic\\\\nFoundation, New Orleans, LA5The University of Queensland Medical School, Ochsner Clinical School, New Orleans, LA\\\\nBackground: Coffeeisawidelyavailablebeveragethatisenjoyedbyindividualsofmanycultures.Thepublicationofnewstudies\\\\npromptsareviewoftheclinicalupdatesregardingtheassociationbetweencoffeeconsumptionandcardiovasculardisease.\\\\nMethods: Wepresentanarrativereviewoftheliteraturerelatedtocoffeeconsumptionandcardiovasculardisease.\\\\nResults: Recent(2000-2021)studieshaveshownthatregularcoffeeconsumptionisassociatedwithadecreasedriskofdeveloping\\\\nhypertension,heartfailure,andatrialfibrillation.However,resultsareinconsistentwithregardtocoffeeconsumptionandriskof\\\\ndevelopingcoronaryheartdisease.MoststudiesshowaJ-shapedassociation,whereinmoderatecoffeeconsumptionresultedin\\\\ndecreasedriskofcoronaryheartdiseaseandheavycoffeeconsumptionresultedinincreasedrisk.Inaddition,boiledorunfiltered\\\\ncoffeeismoreatherogenicthanfilteredcoffeebecauseofitsrichditerpenecontentthatinhibitsbileacidsynthesisandultimately\\\\naffectslipidmetabolism.Ontheotherhand,filteredcoffee,whichisessentiallydevoidoftheaforementionedcompounds,exerts\\\\nantiatherogenic properties by increasing high-density lipoprotein\\\\u2013mediated cholesterol efflux from macrophages through the\\\\ninfluenceofplasmaphenolicacid.Assuch,cholesterollevelsareprincipallyinfluencedbythemannerofcoffeepreparation(boiled\\\\nvsfiltered).\\\\nConclusion: Ourfindingssuggestthatmoderatecoffeeconsumptionleadstoadecreaseinall-causeandcardiovascular-related\\\\nmortality, hypertension, cholesterol, heart failure, and atrial fibrillation. However, no conclusive relationship between coffee and\\\\ncoronaryheartdiseaseriskhasbeenconsistentlyidentified.\\\\nKeywords: Atrialfibrillation,cholesterol,coffee,coronarydisease,diterpenes,heartfailure,hypertension,lipids,phenolicacid\\\\nAddress correspondence to Michael F. Mendoza, MD, The Gayle and Tom Benson Cancer Center, Ochsner Clinic Foundation, 1514 Jefferson\\\\nHwy., New Orleans, LA 70121. Tel: (504) 842-4482. Email: michael.mendoza@ochsner.org\\\\nINTRODUCTION\\\\nCoffee, one of the most popular beverages in the world,\\\\nis widely enjoyed regardless of individuals\\\\u2019 ethnicity, sex,\\\\nor cultural background because of its psychoactive effects,\\\\nincluding mental alertness, vigilance, reaction time, and\\\\nproductivity. Its accessibility and extensive consumption\\\\nhave generated great interest regarding its overall impact\\\\non health. Concerns have been raised about the ability of\\\\ncoffee to induce cardiac arrhythmias and increase blood\\\\npressure.\\\\n1,2 Inthe1960s,coffeeconsumptionwaslabeledas\\\\na cardiovascular risk factor associated with coronary heart\\\\ndisease.\\\\n3\\\\nAmericans, similar to Europeans, are estimated to con-\\\\nsume approximately 5.1 kg of coffee per person per year.4\\\\nThe amount of caffeine, a major component of coffee, varies\\\\nbetween 30 mg and 175 mg in a single home-prepared cup\\\\nof coffee.4 The stimulant effect of caffeine is caused by\\\\nthe antagonism of adenosine receptors, effectively inhibit-\\\\ning the effects of adenosine, a well-known inhibitory neu-\\\\nromodulator. However, caffeine is not a completely benign\\\\ncompound, as it can cross the placenta during pregnancy\\\\nand may potentially cause conditions such as sponta-\\\\nneous abortion and impaired fetal growth. Therefore, cof-\\\\nfee consumption for females who are pregnant or plan-\\\\nning to become pregnant should be limited to a moder-\\\\nate level that does not exceed 300 mg of caffeine per\\\\nday.\\\\n5\\\\nGiven the publication of recent (2000-2021) studies\\\\nregarding coffee consumption, we review clinical updates\\\\nregarding the impact of coffee consumption on cardio-\\\\nvascular health. This review focuses on the association\\\\nbetween coffee consumption and cardiovascular disease\\\\u2013\\\\nrelated mortality and morbidity.\\\\nMETHODS\\\\nWe conducted a literature search of the PubMed/\\\\nMEDLINE database for relevant articles using a combina-\\\\ntion of key terms such as \\\\u201ccoffee,\\\\u201d \\\\u201ccoffee consumption,\\\\u201d\\\\n\\\\u201ccardiovascular diseases,\\\\u201d \\\\u201chypertension,\\\\u201d \\\\u201ccholesterol,\\\\u201d\\\\n\\\\u201cmyocardial infarct,\\\\u201d and \\\\u201catrial fibrillation.\\\\u201d We included\\\\nstudiesthatinvestigatedtheassociationofcoffeeconsump-\\\\ntion and various cardiac conditions. This narrative review\\\\nsynthesizesfindingsfrompreviousresearchandrecentstud-\\\\nies on the topic.\\\\n152 OchsnerJournal Mendoza, MF\\\\nCOFFEE CONSUMPTION AND HYPERTENSION\\\\nA 1999 meta-analysis of clinical trials by Jee et al\\\\nthat included 11 eligible studies (n=522) revealed a direct\\\\nincreased relationship between coffee consumption and\\\\nblood pressure readings after a 56-day median follow-up.6\\\\nAnoldercohortstudybyJenneretal(1988)thatincluded340\\\\nworking males aged 20 to 45 years old who were not on any\\\\nantihypertensivemedicationfora6-yearperiodrevealedthat\\\\nsystolic and diastolic changes in blood pressure were both\\\\npositively related to baseline age and weight.\\\\n7 In the Jenner\\\\netalstudy,areductionincoffeeconsumptionwasnegatively\\\\nassociated with systolic changes in blood pressure.\\\\n7\\\\nHowever, more recent studies have reported contrast-\\\\ning findings. A large cohort study (n =8,780) of middle-\\\\naged adults from Brazil by Miranda et al (2021) showed\\\\nthat those who consumed moderate (1 to 3 cups per day)\\\\namounts of coffee had less risk of developing hyperten-\\\\nsion than those who never or almost never drank coffee\\\\n(relative risk [RR]=0.82, 95% CI 0.68 to 0.97,P=0.018).\\\\n8\\\\nNotably, these benefits were only observed in those who\\\\nhad never smoked (RR=0.79, 95% CI 0.64 to 0.98) as\\\\nopposed to current and former smokers who did not show\\\\na statistically significant reduction in relative risk.\\\\n8 In a pilot\\\\ncrossover randomized study by Revuelta-Iniesta and Al-\\\\nDujaili (2014), green coffee was found to significantly reduce\\\\nsystolic blood pressure (P=0.02) by a mean of 2.65 \\\\u00b1\\\\n1.37 mm Hg compared to baseline.\\\\n9\\\\nA 2018 review by Fan et al proposed several possible\\\\nmechanisms underlying these results: (1) the augmentation\\\\nofcytochromeP4501A2(CYP1A2)activity(themainenzyme\\\\nfor metabolizing caffeine), which is inversely correlated with\\\\nblood pressure levels in coffee drinkers who are nonsmok-\\\\ners; (2) the inhibition of sodium and water reabsorption;\\\\nand (3) the inhibition of inflammation, oxidative stress, and\\\\ntherenin-angiotensin-aldosteronesystem(RAAS)viachloro-\\\\ngenicacid,whichisfoundinhighconcentrationsincoffee.\\\\n10\\\\nIn 2009, the Hypertension and Ambulatory Recording VEne-\\\\ntiaSTudy(HARVEST)foundthattheriskofdevelopinghyper-\\\\ntensionwasdirectlyassociatedwithcoffeeconsumptionbut\\\\nonly in people who possessed the allele CYP1A2 variant\\\\nfor slow metabolizers (59% of the population); whereas in\\\\nthose who were rapid CYP1A2 metabolizers, coffee con-\\\\nsumption was inversely related to the risk of developing\\\\nhypertension.\\\\n11\\\\nCOFFEE CONSUMPTION AND CHOLESTEROL\\\\nAs stated previously, boiled or unfiltered coffee is more\\\\natherogenicthanfilteredcoffeebecauseofitsditerpenecon-\\\\ntent. Cafestol and kahweol are 2 diterpenes in coffee bever-\\\\nages, with approximately 7.2 mg of each substance per cup\\\\nof boiled coffee.\\\\n12 However, paper-filtering coffee removes\\\\nmost of these oils, with only about 0.02 mg of each sub-\\\\nstance retained per cup.\\\\n12-14 Post et al (1997) found that\\\\nditerpenes inhibit bile acid synthesis which leads to atten-\\\\nuated catabolism of lipids.15 The researchers observed that\\\\ncafestol suppressed cholesterol 7\\\\u03b1-hydroxylase and sterol\\\\n27-hydroxylase in rat hepatocytes, while kahweol had less\\\\nsuppressive effects.15\\\\nBecauseboiledcoffeeisknowntohaveatherogeniccapa-\\\\nbilities through cafestol and kahweol, filtered coffee that is\\\\nvirtually devoid of these compounds can exert antiathero-\\\\ngenic properties by increasing high-density lipoprotein\\\\u2013\\\\nmediated cholesterol efflux from macrophages through the\\\\ninfluenceofplasmaphenolicacid,anothermajorcomponent\\\\nin coffee beverages. Uto-Kondo et al (2010) concluded that\\\\nplasma phenolic acid is capable of increasing ATP-binding\\\\ncassette transporter ABCG1 and scavenger receptor class\\\\nB type I (SR-BI) expression, which are responsible for high-\\\\ndensity lipoprotein\\\\u2013mediated cellular cholesterol efflux.\\\\n16\\\\nFurthermore, coffee consumption was observed to have\\\\na direct linear relationship with total cholesterol levels.17\\\\nResearchers later (in 1987 and 1989) found that between\\\\nunfiltered (boiled) and filtered coffee, only boiled coffee\\\\nwas directly associated with an increase in total cholesterol\\\\nlevels.18,19 Acrossover,randomized,controlledstudybySar-\\\\nri\\\\u00e1 et al (2018) of 25 normocholesterolemic and 27 hyper-\\\\ncholesterolemic males and females aged 18 to 45 years\\\\nwith body mass index 18 to 25 kg/m2 found significant\\\\ndecreases in systolic and diastolic blood pressure (P=0.001\\\\nandP<0.001, respectively) in both groups, as well as in per-\\\\ncentage of body fat (P=0.001) after 3 servings per day of a\\\\ngreen/roasted coffee blend, providing 510.6 mg hydroxycin-\\\\nnamicacidsand121.2mgcaffeineperday,vsacontroldrink\\\\n(8 weeks each).20 Concurrent significant decreases were\\\\nseen in leptin (P=0.001), plasminogen activator inhibitor 1\\\\n(P<0.001), and resistin (P=0.034) levels, as well as glucose\\\\nconcentration (P=0.030), insulin resistance (P=0.011), and\\\\ntriglyceride levels (P= 0.017) in the 2 groups after coffee\\\\nconsumption, with a notably greater reduction in the hyper-\\\\ncholesterolemic cohort (group effect,P=0.027).20 Currently,\\\\nno specific recommendations on the type and ideal amount\\\\nof coffee consumption take advantage of these findings.\\\\nCOFFEE CONSUMPTION, CORONARY HEART\\\\nDISEASE, AND CARDIOVASCULAR DISEASE\\\\nDespite evidence that cholesterol levels seem to be\\\\nincreased by boiled coffee consumption,18,19 the associa-\\\\ntion with coronary heart disease seems to be different. In\\\\na prospective cohort study by Lopez-Garcia et al (2006),\\\\ngroups with varying coffee consumption had insignificant\\\\nRRs for coronary heart disease.\\\\n21 However, results across\\\\nstudies are inconsistent. In an Italian study by Grioni et al\\\\n(2015), the consumption of more than 2 cups per day of\\\\nItalian-style coffee was associated with an increased risk\\\\nof coronary heart disease.\\\\n12 Additionally, a meta-analysis of\\\\n13 case-control and 10 cohort studies by Sofi et al (2007)\\\\nshowed a significant association between high coffee con-\\\\nsumption and risk of coronary heart disease in the case-\\\\ncontrol studies:>4 cups per day (odds ratio [OR] 1.83, 95%\\\\nCI1.49to2.24, P<0.0001)and3to4cupsperday(OR1.33,\\\\n95% CI 1.04 to 1.71,P<0.0001).\\\\n22 In the long-term follow-\\\\nup cohort studies, however, the risk of developing coronary\\\\nheart disease was insignificant for those drinking>4c u p s\\\\nper day (RR 1.16, 95% CI 0.95 to 1.41,P=0.14), 3 to 4 cups\\\\nperday(RR1.05,95%CI0.90to1.22, P=0.57),and /22642cups\\\\nper day (RR 1.04, 95% CI 0.90 to 1.19,P=0.60).22\\\\nInastudybyRodriguez-ArtalejoandL\\\\u00f3pez-Garcia(2018),\\\\nmoderate levels of coffee consumption (3 to 5 cups per day)\\\\nwere associated with a 15% reduction in the risk of car-\\\\ndiovascular disease, and higher levels of intake were not\\\\nshown to increase risk.\\\\n23 In a study by Zhou and Hypp\\\\u00f6-\\\\nnen (2019), those who did not drink coffee, those who drank\\\\ndecaffeinatedcoffee,andheavycoffeedrinkers( >6cupsper\\\\nday) had higher odds of developing cardiovascular disease\\\\nVolume23,Number2,Summer2023 153 Coffee Consumption and Cardiovascular Health\\\\nby 11%, 7%, and 22%, respectively (P=0.013) compared to\\\\nthose who consumed 1 to 2 cups of coffee per day.24\\\\nIn a meta-analysis of 17 studies involving 233,617 partici-\\\\npants,Moetal(2018)notedanincreaseinmyocardialinfarc-\\\\ntionamongmaleswhoconsumed >3cupsofcoffeeperday;\\\\nthis effect was not observed in females.25 Inconsistencies\\\\nhave also been seen among elderly males and females. A\\\\nstudybyvanWoudenberghetal(2008)revealedasignificant\\\\nreduction in coronary calcification in elderly (mean age of 64\\\\nyears) females with moderate (3 to 4 cups per day) and high\\\\n(>4 cups per day) coffee intake compared to those with a\\\\ndaily intake of/22643c u p s .\\\\n26 The investigators speculated that\\\\nthe phytoestrogens in coffee could partly replace estrogen\\\\nstores in postmenopausal females, leading to a decreased\\\\nincidence of atherosclerosis. This function of phytoestro-\\\\ngen may explain the lack of protective effect of coffee for\\\\natherosclerotic calcification in males.\\\\n26\\\\nCornelis et al (2006) shed some light on why these stud-\\\\nies commonly reported a dose-dependent J- or U-shaped\\\\ncurve.\\\\n27 According to their study, the increased risk of coro-\\\\nnary heart disease among boiled (unfiltered) coffee con-\\\\nsumers is associated with diterpenes that increase choles-\\\\nterol levels and ultimately the risk of coronary heart dis-\\\\nease. However, Cornelis et al noted that the risk of devel-\\\\noping myocardial infarction was not obviated by filtering\\\\nditerpenoids.\\\\n27 Variations in CYP1A2 activity among coffee\\\\nconsumers determined the risk of cardiovascular disease,\\\\nand because CYP1A2 does not metabolize anything else in\\\\nfiltered coffee other than caffeine, the investigators were led\\\\nto believe that caffeine is the major component of filtered\\\\ncoffee that increases the risk of myocardial infarction. They\\\\nproposed that the inhibition of the vasodilatory effects of\\\\nadenosine may play a role in the development of cardio-\\\\nvascular disease. This hypothesis is noteworthy, as coffee\\\\ndoesnotincreasetheriskofhypertension,possiblyowingto\\\\nits other antihypertensive effects (diuresis, RAAS inhibition,\\\\nand antioxidant properties). Cornelis et al reported that the\\\\nriskofnonfatalmyocardialinfarctiondependedontheability\\\\nof an individual to metabolize caffeine.\\\\n27 CYP1A2 accounts\\\\nfor approximately 95% of caffeine metabolism, and great\\\\nvariability in enzyme activity is observed in individuals. The\\\\ncarriers of the variant allele CYPA12*1F are slow caffeine\\\\nmetabolizers, while those who are homozygous with the\\\\nCYP1A2*1A allele are rapid metabolizers.\\\\n27 This genetic dif-\\\\nference could potentially explain the variable results noted\\\\nacross studies. The Cornelis et al study indicated a posi-\\\\ntive correlation between increased coffee consumption and\\\\nthe risk of nonfatal myocardial infarction but only in those\\\\nwho were slow metabolizers of caffeine.\\\\n27 However, when\\\\nsmoking was involved, the results were once again conflict-\\\\ningbecausesmokinginducesCYP1A2activity,andthemag-\\\\nnitude of CYP1A2 induction was less pronounced in those\\\\nwho had the variant allele CYPA12*IF. The risk of myocar-\\\\ndial infarction was higher in those who were slow caffeine\\\\nmetabolizers regardless of smoking status. While smoking\\\\nmay appear to decrease the risk of myocardial infarction\\\\nby induction of the homozygous allele, smokers with the\\\\nCYP1A2*1A allele do not necessarily bode better than slow\\\\nmetabolizers because smoking is an established indepen-\\\\ndentcardiovasculardiseaseriskfactorwithotherpathologic\\\\nmechanisms beyond the protective effects of CYP1A2 on\\\\ncaffeine regulation.\\\\n27\\\\nThegeneticassociationsidentifiedbyCornelisetal 27 were\\\\nnot observed in the large prospective analysis by Zhou and\\\\nHypp\\\\u00f6nen (2019).24\\\\nResults from these studies conflict, and the study designs\\\\ninclude many possible confounders. The standardization of\\\\ncoffee preparation and intake is an important issue because\\\\nthe definition of light, moderate, and heavy consumption is\\\\nnot consistent across studies. As such, more studies are\\\\nneeded to reach a solid consensus about the impact of cof-\\\\nfee consumption on cardiovascular disease, specifically at\\\\nhigher intake levels.\\\\nCOFFEE CONSUMPTION AND\\\\nCARDIOVASCULAR DISEASE POST\\\\nMYOCARDIAL INFARCTION\\\\nIn a study by Silletta et al (2007), no association was\\\\nfound between moderate coffee consumption and cardio-\\\\nvascular disease events in patients who had had a myocar-\\\\ndial infarction.\\\\n28 After a mean follow-up of 3.5 years, coffee\\\\nconsumption did not change the risk of developing coro-\\\\nnary heart disease, stroke, or sudden cardiac death in those\\\\nwho had previous myocardial infarction. These results are\\\\nnot substantially reliable because the trend finding across\\\\ncategories of coffee consumption was not statistically sig-\\\\nnificant (P=0.18).\\\\n28 A meta-analysis by Brown et al (2016)\\\\nfound a statistically significant inverse correlation between\\\\ncoffee consumption and mortality (n=3,271).\\\\n29 Light coffee\\\\ndrinkers (1 to 2 cups per day) vs those who did not drink\\\\ncoffee were associated with a risk ratio of 0.79 (95% CI 0.66\\\\nto 0.94,P=0.008), while heavy coffee drinkers (>2c u p sp e r\\\\nday) vs those who did not drink coffee were associated with\\\\na risk ratio of 0.54 (95% CI 0.45 to 0.65,P<0.00001). Heavy\\\\ncoffee drinkers vs light coffee drinkers had a risk ratio of\\\\n0.69 (95% CI 0.58 to 0.83,P<0.0001).\\\\n29 These results were\\\\nsupported by a 2020 meta-analysis of 6 prospective stud-\\\\nies showing that coffee consumption was associated with\\\\nlower risk of cardiovascular mortality (hazard ratio [HR] 0.70,\\\\n95% CI 0.54 to 0.91, I\\\\n2=0%; 2 studies) and not associated\\\\nwith an increased risk of all-cause mortality (HR 0.85, 95%\\\\nCI 0.63 to 1.13, I2=50%; 3 studies), recurrent myocardial\\\\ninfarction (HR 0.99, 95% CI 0.80 to 1.22, I2=0%; 3 stud-\\\\nies), or stroke (HR=0.97, 95% CI 0.63 to 1.49, I2=39%;\\\\n2 studies).30\\\\nCOFFEE CONSUMPTION AND HEART FAILURE\\\\nData on diet and food intake from the Framingham Heart\\\\nStudy (FHS), the Cardiovascular Health Study (CHS), and\\\\nthe Atherosclerosis Risk in Communities (ARIC) study were\\\\nstudied to identify potential lifestyle and behavioral factors\\\\nassociated with heart failure. Stevens et al (2021) showed\\\\nan inverse association between coffee consumption and the\\\\nriskofheartfailureinall3studies.\\\\n31 DatafromtheFHS,CHS,\\\\nandARICshowedthathighercoffeeconsumptionwasasso-\\\\nciated with a lower long-term risk of heart failure.31 Mostof-\\\\nsky et al (2012) also observed a statistically significant J-\\\\nshaped relationship between coffee consumption and heart\\\\nfailure; those who consumed up to 4 servings of coffee per\\\\nday had a strong inverse relationship with the development\\\\nof heart failure.32 Those who tended to consume coffee at\\\\nmuch higher levels (starting at 9 to 10 servings per day) had\\\\na potentially higher risk of heart failure.32 Mostofsky et al\\\\nfound no evidence that sex, baseline history of myocardial\\\\n154 OchsnerJournal\", \"chunk_size\": 7270, \"chunk_index\": 0, \"cut_type\": \"sentence_cut\", \"id\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"color\": \"#801212\"}, {\"name\": \"diterpenes\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Compounds known to affect lipid metabolism, found in coffee.\", \"id\": \"2e1cc3a7-b555-53ac-8239-1d6793d51b6e\", \"color\": \"#f47710\"}, {\"name\": \"concept\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"concept\", \"id\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"color\": \"#6510f4\"}, {\"name\": \"unfiltered coffee\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Coffee prepared without a filter, retaining more diterpenes.\", \"id\": \"d5c90c81-efa1-5a49-98d7-50e43440c18c\", \"color\": \"#f47710\"}, {\"name\": \"atrial fibrillation\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"An irregular heartbeat that can lead to blood clots, stroke, and other heart-related complications.\", \"id\": \"7772ab5b-e0ed-5eab-801a-c36740862804\", \"color\": \"#f47710\"}, {\"name\": \"caffeine metabolism\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"The biochemical processing of caffeine in the body.\", \"id\": \"9569c511-9ddc-5026-bf1e-5f8e7092558a\", \"color\": \"#f47710\"}, {\"name\": \"2023\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"The year of publication of the study.\", \"id\": \"7073fe83-625c-597f-8497-9da0fc02510b\", \"color\": \"#f47710\"}, {\"name\": \"date\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"date\", \"id\": \"d61d99ac-b291-5666-9748-3e80e1c8b56a\", \"color\": \"#6510f4\"}, {\"name\": \"TOJ-22-0073_152Mendoza\", \"type\": \"PdfDocument\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"raw_data_location\": \"/Users/borisarzentar/Projects/Topoteretes/cognee/examples/data/scientific_papers/TOJ-22-0073_152Mendoza.pdf\", \"external_metadata\": \"{}\", \"mime_type\": \"application/pdf\", \"id\": \"a2a2969f-2efa-5d9c-96f1-60b2d106641b\", \"color\": \"#D3D3D3\"}, {\"name\": \"coronary heart disease\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A disease characterized by the narrowing or blockage of the coronary arteries.\", \"id\": \"6ec740cf-ccfb-57ba-8489-41caf3605aa6\", \"color\": \"#f47710\"}, {\"name\": \"carl j. lavie\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author, MD at Department of Cardiology, Ochsner Clinic Foundation, New Orleans, LA.\", \"id\": \"678c66ec-12bf-50ce-8325-03731de6e10c\", \"color\": \"#f47710\"}, {\"name\": \"michael f. mendoza\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author, MD at The Gayle and Tom Benson Cancer Center, Ochsner Clinic Foundation, New Orleans, LA.\", \"id\": \"a0c86064-a0d8-5c1d-999f-a8e20ad4e784\", \"color\": \"#f47710\"}, {\"name\": \"therese posas-mendoza\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author, MD at Department of Rheumatology, Ochsner Clinic Foundation, Covington, LA.\", \"id\": \"f3c82751-703d-598c-9f2c-332c08ebbb1d\", \"color\": \"#f47710\"}, {\"name\": \"ralf martz sulague\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author, MD at School of Health, Georgetown University, Washington, DC.\", \"id\": \"1b9533e0-f89c-5cfd-be59-d31448fff700\", \"color\": \"#f47710\"}, {\"name\": \"heart failure\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A chronic condition in which the heart does not pump blood as well as it should.\", \"id\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"color\": \"#f47710\"}, {\"name\": \"phenolic acid\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A compound found in coffee that influences cholesterol metabolism.\", \"id\": \"39dee7b2-b681-5c4a-96cd-8d5119bcbd7d\", \"color\": \"#f47710\"}, {\"name\": \"cardiovascular health\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A branch of medicine that deals with diseases and conditions of the heart and blood vessels.\", \"id\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"color\": \"#f47710\"}, {\"name\": \"filtered coffee\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Coffee prepared using a filter that removes certain compounds.\", \"id\": \"b15d8f44-a728-5257-80ed-ec1c87a507f9\", \"color\": \"#f47710\"}, {\"name\": \"\", \"type\": \"DocumentChunk\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Mendoza, MF\\\\ninfarction, or diabetes mellitus affected outcomes.32 From\\\\ntheCoronaryArteryRiskDevelopmentinYoungAdultsstudy\\\\n(n=2,735) published by the European Society of Cardiol-\\\\nogy(2020),lowtomoderatecoffeeconsumptionfromyoung\\\\nadulthoodtomiddleagewasassociatedwithbetterleftven-\\\\ntricular systolic and diastolic function.33\\\\nAlthoughresultsseemtobeconsistentacrossstudies,the\\\\npotential mechanisms causing reduction in heart failure risk\\\\nare not well understood. A close look into the biomolecular\\\\nprocesses is warranted to strengthen causality.\\\\nCOFFEE CONSUMPTION AND ATRIAL\\\\nFIBRILLATION\\\\nBodar et al (2019) found that consumption of 1 to 3\\\\ncups of coffee per day was associated with lower rates of\\\\natrial fibrillation.34 After adjusting for age, smoking status,\\\\nalcohol intake, and exercise, those who consumed /22641\\\\ncup per week, 2 to 4 cups per week, and 5 to 6 cups per\\\\nweek were analyzed. In these subgroups, HRs were 0.85\\\\n(95% CI 0.71 to 1.02), 1.07 (95% CI 0.88 to 1.30), and\\\\n0.93 (95% CI 0.74 to 1.17), respectively. Among those who\\\\nconsumed 1 cup per day, 2 to 3 cups per day, and>4c u p s\\\\nper day, corresponding HRs were 0.85 (95% CI 0.74 to\\\\n0.98), 0.86 (95% CI 0.76 to 0.97), and 0.96 (95% CI 0.80 to\\\\n1.14), respectively, after adjusting for age, smoking, alcohol\\\\nintake, and exercise (P for nonlinear trend=0.01). These\\\\nresults indicate that those who drank 1 to 3 cups of coffee\\\\nper day had less risk of atrial fibrillation compared to other\\\\nintakefrequencies.\\\\n34 Ameta-analysisofprospectivecohorts\\\\nby Cheng et al (2014) showed an 11% reduction in atrial\\\\nfibrillation risk for low coffee consumption equivalent to\\\\n<500 mg of caffeine per day (RR 0.89, 95% CI 0.80 to 0.99,\\\\nP=0.032, I\\\\n2=30.9%, P=0.227) and 16% for high coffee\\\\nconsumption equivalent to/2265500 mg of caffeine per day (RR\\\\n0.84, 95% CI 0.75 to 0.94,P=0.002, I2=24.1%, P=0.267)\\\\nafter pooling of results from studies with adjustment of\\\\npotential confounders.\\\\n35 A theory proposed to explain these\\\\nresults is that coffee promotes anti-inflammatory processes\\\\nthrough its high levels of antioxidants such as cafestol,\\\\npolyphenol, trigonelline, chlorogenic acid, and quinine.\\\\n34,36\\\\nA meta-analysis of 23 randomized controlled trials by\\\\nAli-Hassan-Sayegh et al (2014) reported that antioxidants\\\\nsuch as N-acetylcysteine and polyunsaturated fatty acids\\\\nhave a protective role in the prevention of atrial fibrillation\\\\nafter cardiac surgery.\\\\n37 Patients who were infused with\\\\nthese antioxidant compounds experienced less incidence\\\\nof atrial fibrillation after cardiac surgery.37 These results may\\\\nsuggest that coffee consumption, especially in moderation,\\\\nmay induce anti-inflammatory effects that may attenuate\\\\nthe risk of developing atrial fibrillation.\\\\nCOFFEE CONSUMPTION AND MORTALITY\\\\nA large pool of data indicates that coffee consumption\\\\nis not associated with increased cardiovascular disease\\\\nmortality. Results presented by Ding et al (2015) from 3\\\\nwell-known large prospective cohort studies, the Nurses\\\\u2019\\\\nHealthStudy,theHealthProfessionalsFollow-upStudy,and\\\\nthe Nurses\\\\u2019 Health Study-II, showed a nonlinear associa-\\\\ntion between cardiovascular disease mortality and coffee\\\\nconsumption.\\\\n38 In the analysis of the aforementioned cohort\\\\nstudies, moderate coffee consumption was associated with\\\\nlessmortality,andhigherlevelsofconsumptiondidnotresult\\\\nin increased deaths after removing the confounding effects\\\\nof smoking history. As such, the nonlinear relationship was\\\\nstrengthenedbyremovingtheresidualconfoundingeffectof\\\\nsmoking status. The authors concluded from their analysis\\\\nthat the results extracted from these 3 large cohort studies\\\\nindicate that coffee consumption can be incorporated into a\\\\nhealthy lifestyle.\\\\n38\\\\nThe cohort study of Lopez-Garcia et al (2008) revealed\\\\naninverserelationshipbetweencoffeeconsumptionandall-\\\\ncause mortality, principally because of a moderate reduc-\\\\ntion in risk for cardiovascular disease\\\\u2013related mortality in\\\\nboth males (P for trend=0.008) and females (P for trend\\\\n<0.001).\\\\n39 The authors noted that a possible mechanism\\\\nfor such an outcome was the strong antioxidant capacity of\\\\ncoffee compounds other than caffeine such as chlorogenic\\\\nacid,ferulicacid,andp-Coumaricacid.Theyalsonotedthat\\\\nother substances in coffee such as magnesium, trigonelline,\\\\nand quinides improve insulin sensitivity. Despite the poten-\\\\ntial harmful effects of caffeine and its ability to release\\\\nepinephrine(astronginhibitorofinsulin),theaforementioned\\\\ncompoundsappeartocounterbalancethiseffect.\\\\n39 Inalarge\\\\nprospective cohort study conducted by de Koning Gans\\\\net al (2010), the consumption of black tea and coffee was\\\\nassociated with a lower incidence of coronary heart disease\\\\nmortality.\\\\n40 Andersen et al (2006) reported that consump-\\\\ntion of 1 to 3 cups of coffee per day was associated with\\\\na lower incidence of cardiovascular disease\\\\u2013related mortal-\\\\nity (HR 0.76, 95% CI 0.64 to 0.91,P=0.005) in females com-\\\\nparedtoconsumptionof >4cupsperday .41 Anearlierstudy\\\\nby Kleemola et al (2000) noted a decrease in total mortal-\\\\nity among females drinking>7c u p so fc o f f e ep e rd a y( r i s k\\\\nratio0.62,95%CI0.44to0.87),evenafteradjustingforage,\\\\nsmoking status, serum cholesterol level, blood pressure,\\\\nand history of myocardial infarction.42 Lopez-Garcia et al\\\\n(2008) found a reduction in RR for all-cause mortality among\\\\nfemales: RR of 0.93 (95% CI 0.87 to 0.98) for those drink-\\\\ning 5 to 7 cups per week; RR of 0.82 (95% CI 0.77 to 0.87)\\\\nfor those drinking 2 to 3 cups per day; RR of 0.74 (95% CI\\\\n0.68to0.81)forthosedrinking4to5cupsperday;andRRof\\\\n0.83(95%CI0.73to0.95)forthosedrinking /22656cupsperday\\\\n(P for trend<0.001).\\\\n39 In fact, most studies show an overall\\\\nreductioninmortality,althoughsomestudieshaveproduced\\\\nconflicting results. The FHS showed that coffee consump-\\\\ntion in the elderly population was associated with a 43%\\\\nreduction in coronary heart disease\\\\u2013related deaths.\\\\n31 Fur-\\\\nthermore, a large meta-analysis (40 studies, n=3,852,651)\\\\nby Kim et al (2019) revealed that coffee consumption was\\\\ninverselyrelatedtoall-causemortality. 43 Thetotalnumberof\\\\ndeaths from all categories was 450,256; among coffee con-\\\\nsumers, the intakes with the lowest RRs were 3.5 cups per\\\\ndayforall-causemortality(RR0.85,95%CI0.82to0.89),2.5\\\\ncups per day for cardiovascular disease mortality (RR 0.83,\\\\n95% CI 0.80 to 0.87), and 2 cups per day for cancer mortal-\\\\nity (RR0.96, 95% CI, 0.94 to 0.99). The inverse relationship\\\\nbetween mortality and coffee consumption in nonsmokers\\\\n(RR 0.95, 95% CI 0.93 to 0.97) was slightly stronger than in\\\\nsmokers (RR 0.97, 95% CI 0.96 to 0.99), although the differ-\\\\nence was not statistically significant (P=0.33). No additional\\\\nbenefit was seen with additional caffeine intake. In conclu-\\\\nsion, moderate coffee consumption was deemed beneficial\\\\nto overall health. However, the associations were stronger\\\\nin Europeans and Asians compared to Americans living in\\\\nVolume23,Number2,Summer2023 155 Coffee Consumption and Cardiovascular Health\\\\ntheUnitedStates. 43 Studiesareneededtounderstandthese\\\\ndemographic differences.\\\\nDISCUSSION\\\\nCoffee has the physiologic effect of raising blood pres-\\\\nsure, although the effect appears to be transient and does\\\\nnot affect the propensity to develop overt hypertension.\\\\nLikewise, data have shown that moderate consumption\\\\nof coffee is associated with less risk of hypertension but\\\\nprincipally in those who never smoked or do not smoke and\\\\nin those who are fast metabolizers of caffeine. Boiled coffee\\\\nis atherogenic because of its rich diterpene content, namely\\\\ncafestol and kahweol, that inhibits bile acid synthesis and\\\\nultimately affects lipid metabolism. On the other hand,\\\\nfiltered coffee, which is essentially devoid of the aforemen-\\\\ntioned compounds, exerts antiatherogenic properties by\\\\nincreasing high density lipoprotein\\\\u2013mediated cholesterol\\\\nefflux from macrophages through the influence of plasma\\\\nphenolic acid. As such, cholesterol levels are influenced\\\\nby the manner of coffee preparation (boiled vs filtered).\\\\nIn terms of the risk of developing cardiovascular disease,\\\\nstudies are inconsistent with regard to coffee consumption\\\\nand risk of coronary heart disease, with discrepancies\\\\nnoted depending on sex, genetics, and smoking status. The\\\\nmajority of studies showed a J-shape association in which\\\\nmoderate coffee consumption was associated with a lower\\\\nrisk of coronary heart disease compared to heavy coffee\\\\nconsumption which was associated with an increased\\\\nrisk of coronary heart disease. These findings point to the\\\\nimportance of moderate coffee consumption because of\\\\nthe potential risk of cardiovascular disease. Regarding heart\\\\nfailure, results appear to be consistent across studies. The\\\\nFHS, CHS, and ARIC studies showed that high coffee intake\\\\nwas associated with a decrease in long-term risk of heart\\\\nfailure independent of sex, baseline history of myocardial\\\\ninfarction, and diabetes. Because of the lack of understand-\\\\ningofpotentialmechanismsbehindreductioninheartfailure\\\\nrisk, more studies are needed. Moderate coffee consump-\\\\ntion was also found to attenuate the risk of atrial fibrillation,\\\\npossibly owing to its strong anti-inflammatory components\\\\nsuch as cafestol, polyphenol, trigonelline, chlorogenic acid,\\\\nand quinide. Studies have shown moderate coffee con-\\\\nsumption to be associated with a reduction in all-cause\\\\nand cardiovascular disease\\\\u2013related mortality, whereas\\\\nhigher amounts of coffee consumption were detrimental\\\\nto health.\\\\nCONCLUSION\\\\nOur review suggests that moderate coffee consumption\\\\nis associated with a decrease in all-cause and cardiovas-\\\\ncular disease\\\\u2013related mortality, hypertension, cholesterol,\\\\nheartfailure,andatrialfibrillation,whileconsensusislacking\\\\nregarding the association between coffee consumption and\\\\ntheriskofdevelopingcardiovasculardisease.Despiteprevi-\\\\nous concerns about coffee consumption being a significant\\\\ncoronaryheartdiseaseriskfactor,mostmodernprospective\\\\ncohort meta-analyses found no association between coffee\\\\nconsumption and coronary heart disease. However, results\\\\nare inconsistent across studies. Most favorable outcomes\\\\nareassociatedwithmoderatecoffeeconsumption;however,\\\\nthere is no current consensus on the definition of moderate\\\\ncoffee consumption. Further, genetics possibly play a large\\\\nrole in determining hypertension and cardiovascular disease\\\\noutcomes. This review illustrates that coffee is a complex\\\\nmixture of compounds that may cause both harm and ben-\\\\nefit. As such, additional studies are needed to further eluci-\\\\ndate the ideal way to consume coffee, not only as a drink\\\\nto be enjoyed, but also as a drink with protective health\\\\nbenefits.\\\\nACKNOWLEDGMENTS\\\\nThe authors have no \\\\ufb01nancial or proprietary interest in the\\\\nsubject matter of this article.\\\\nREFERENCES\\\\n1. RobertsonD,Fr\\\\u00f6lichJC,CarrRK,etal.Effectsofcaffeineon\\\\nplasmareninactivity,catecholaminesandbloodpressure. N\\\\nEnglJMed .1978;298(4):181-186.\\\\ndoi:10.1056/NEJM197801262980403\\\\n2. DobmeyerDJ,StineRA,LeierCV,GreenbergR,SchaalSF.The\\\\narrhythmogeniceffectsofcaffeineinhumanbeings. NEnglJ\\\\nMed.1983;308(14):814-816.\\\\ndoi:10.1056/NEJM198304073081405\\\\n3. PaulO,LepperMH,PhelanWH,etal.Alongitudinalstudyof\\\\ncoronaryheartdisease. Circulation.1963;28(1):20-31.\\\\ndoi:10.1161/01.cir.28.1.20\\\\n4. BonitaJS,MandaranoM,ShutaD,VinsonJ.Coffeeand\\\\ncardiovasculardisease:invitro,cellular,animal,andhuman\\\\nstudies.PharmacolRes.2007;55(3):187-198.\\\\ndoi:10.1016/j.phrs.2007.01.006\\\\n5. BaeJH,ParkJH,ImSS,SongDK.Coffeeandhealth. IntegrMed\\\\nRes.2014;3(4):189-191.doi:10.1016/j.imr.2014.08.002\\\\n6. JeeSH,HeJ,WheltonPK,SuhI,KlagMJ.Theeffectofchronic\\\\ncoffeedrinkingonbloodpressure:ameta-analysisof\\\\ncontrolledclinicaltrials. Hypertension.1999;33(2):647-652.\\\\ndoi:10.1161/01.hyp.33.2.647\\\\n7. JennerDA,PuddeyIB,BeilinLJ,VandongenR.Lifestyle-and\\\\noccupation-relatedchangesinbloodpressureoverasix-year\\\\nperiodinacohortofworkingmen. JHypertensSuppl .\\\\n1988;6(4):S605-S607.\\\\ndoi:10.1097/00004872-198812040-00189\\\\n8. MirandaAM,GoulartAC,Bense\\\\u00f1orIM,LotufoPA,Marchioni\\\\nDM.Coffeeconsumptionandriskofhypertension:a\\\\nprospectiveanalysisinthecohortstudy. ClinNutr.\\\\n2021;40(2):542-549.doi:10.1016/j.clnu.2020.05.052\\\\n9. Revuelta-IniestaR,Al-Dujaili EA.Consumptionofgreencoffee\\\\nreducesbloodpressureandbodycompositionbyinfluencing\\\\n11\\\\u03b2-HSD1enzymeactivityinhealthyindividuals:apilot\\\\ncrossoverstudyusinggreenandblackcoffee. BiomedResInt .\\\\n2014;2014:482704.doi:10.1155/2014/482704\\\\n10. FanL,ZhangHM,CaiJ.Coffeeintakeandbloodpressure. J\\\\nHypertens.2018;36:e258.\\\\ndoi:10.1097/01.hjh.0000539736.03364.12\\\\n11. PalatiniP,CeolottoG,RagazzoF,etal.CYP1A2genotype\\\\nmodifiestheassociationbetweencoffeeintakeandtheriskof\\\\nhypertension.JHypertens.2009;27(8):1594-1601.\\\\ndoi:10.1097/HJH.0b013e32832ba850\\\\n12. GrioniS,AgnoliC,SieriS,etal.Espressocoffeeconsumption\\\\nandriskofcoronaryheartdiseaseinalargeItaliancohort. PLoS\\\\nOne.2015;10(5):e0126550.doi:10.1371/journal.pone.0126550\\\\n13. GrossG,JaccaudE,HuggettAC.Analysisofthecontentofthe\\\\nditerpenescafestolandkahweolincoffeebrews. FoodChem\\\\nToxicol.1997;35(6):547-554.\\\\ndoi:10.1016/s0278-6915(96)00123-8\\\\n14. vanDusseldorpM,KatanMB,vanVlietT,DemackerPN,\\\\nStalenhoefAF.Cholesterol-raisingfactorfromboiledcoffee\\\\n156 OchsnerJournal Mendoza, MF\\\\ndoesnotpassapaperfilter. ArteriosclerThromb.\\\\n1991;11(3):586-593.doi:10.1161/01.atv.11.3.586\\\\n15. PostSM,deWitEC,PrincenHM.Cafestol,the\\\\ncholesterol-raisingfactorinboiledcoffee,suppressesbileacid\\\\nsynthesisbydownregulationofcholesterol7\\\\nalpha-hydroxylaseandsterol27-hydroxylaseinrat\\\\nhepatocytes.ArteriosclerThrombVascBiol .\\\\n1997;17(11):3064-3070.doi:10.1161/01.atv.17.11.3064\\\\n16. Uto-KondoH,AyaoriM,OguraM,etal.Coffeeconsumption\\\\nenhanceshigh-densitylipoprotein-mediatedcholesterolefflux\\\\ninmacrophages. CircRes.2010;106(4):779-787.\\\\ndoi:10.1161/CIRCRESAHA.109.206615\\\\n17. ThelleDS,ArnesenE,F\\\\u00f8rdeOH.TheTroms\\\\u00f8heartstudy.Does\\\\ncoffeeraiseserumcholesterol? NEnglJMed .\\\\n1983;308(24):1454-1457.doi:10.1056/NEJM198306163082405\\\\n18. BakAA,GrobbeeDE.Theeffectonserumcholesterollevelsof\\\\ncoffeebrewedbyfilteringorboiling. NEnglJMed .\\\\n1989;321(21):1432-1437.doi:10.1056/NEJM198911233212103\\\\n19. ThelleDS,HeydenS,FodorJG.Coffeeandcholesterolin\\\\nepidemiologicalandexperimentalstudies. Atherosclerosis.\\\\n1987;67(2-3):97-103.doi:10.1016/0021-9150(87)90270-x\\\\n20. Sarri\\\\u00e1B,Mart\\\\u00ednez-L\\\\u00f3pezS,Sierra-CinosJL,Garc\\\\u00eda-DizL,Mateos\\\\nR,Bravo-ClementeL.Regularlyconsumingagreen/roasted\\\\ncoffeeblendreducestheriskofmetabolicsyndrome. EurJ\\\\nNutr.2018;57(1):269-278.doi:10.1007/s00394-016-1316-8\\\\n21. Lopez-GarciaE,vanDamRM,WillettWC,etal.Coffee\\\\nconsumptionandcoronaryheartdiseaseinmenandwomen:a\\\\nprospectivecohortstudy. Circulation.2006;113(17):2045-2053.\\\\ndoi:10.1161/CIRCULATIONAHA.105.598664\\\\n22. SofiF,ContiAA,GoriAM,etal.Coffeeconsumptionandriskof\\\\ncoronaryheartdisease:ameta-analysis. NutrMetabCardiovasc\\\\nDis.2007;17(3):209-223.doi:10.1016/j.numecd.2006.07.013\\\\n23. Rodr\\\\u00edguez-ArtalejoF,L\\\\u00f3pez-Garc\\\\u00edaE.Coffeeconsumptionand\\\\ncardiovasculardisease:acondensedreviewofepidemiological\\\\nevidenceandmechanisms. JAgricFoodChem .\\\\n2018;66(21):5257-5263.doi:10.1021/acs.jafc.7b04506\\\\n24. ZhouA,Hypp\\\\u00f6nenE.Long-termcoffeeconsumption,caffeine\\\\nmetabolismgenetics,andriskofcardiovasculardisease:a\\\\nprospectiveanalysisofupto347,077individualsand8368\\\\ncases.AmJClinNutr .2019;109(3):509-516.\\\\ndoi:10.1093/ajcn/nqy297\\\\n25. MoL,XieW,PuX,OuyangD.Coffeeconsumptionandriskof\\\\nmyocardialinfarction:adose-responsemeta-analysisof\\\\nobservationalstudies. Oncotarget.2018;9(30):21530-21540.\\\\ndoi:10.18632/oncotarget.23947\\\\n26. vanWoudenberghGJ,VliegenthartR,vanRooijFJ,etal.Coffee\\\\nconsumptionandcoronarycalcification:theRotterdam\\\\nCoronaryCalcificationStudy. ArteriosclerThrombVascBiol .\\\\n2008;28(5):1018-1023.doi:10.1161/ATVBAHA.107.160457\\\\n27. CornelisMC,El-SohemyA,KabagambeEK,CamposH.Coffee,\\\\nCYP1A2genotype,andriskofmyocardialinfarction. JAMA.\\\\n2006;295(10):1135-1141.doi:10.1001/jama.295.10.1135\\\\n28. SillettaMG,MarfisiR,LevantesiG,etal.Coffeeconsumption\\\\nandriskofcardiovasculareventsafteracutemyocardial\\\\ninfarction:resultsfromtheGISSI(GruppoItalianoperloStudio\\\\ndellaSopravvivenzanell\\\\u2019Infartomiocardico)-Prevenzionetrial.\\\\nCirculation.2007;116(25):2944-2951.\\\\ndoi:10.1161/CIRCULATIONAHA.107.712976\\\\n29. BrownOI,AllgarV,WongKY.Coffeereducestheriskofdeath\\\\nafteracutemyocardialinfarction:ameta-analysis. CoronArtery\\\\nDis.2016;27(7):566-572.doi:10.1097/MCA.0000000000000397\\\\n30. RibeiroEM,AlvesM,CostaJ,FerreiraJJ,PintoFJ,CaldeiraD.\\\\nSafetyofcoffeeconsumptionaftermyocardialinfarction:a\\\\nsystematicreviewandmeta-analysis. NutrMetabCardiovasc\\\\nDis.2020;30(12):2146-2158.doi:10.1016/j.numecd.2020.07.016\\\\n31. StevensLM,LinsteadE,HallJL,KaoDP.Associationbetween\\\\ncoffeeintakeandincidentheartfailurerisk:amachinelearning\\\\nanalysisoftheFHS,theARICstudy,andtheCHS. CircHeartFail .\\\\n2021;14(2):e006799.\\\\ndoi:10.1161/CIRCHEARTFAILURE.119.006799\\\\n32. MostofskyE,RiceMS,LevitanEB,MittlemanMA.Habitual\\\\ncoffeeconsumptionandriskofheartfailure:adose-response\\\\nmeta-analysis.CircHeartFail .2012;5(4):401-405.\\\\ndoi:10.1161/CIRCHEARTFAILURE.112.967299\\\\n33. NwabuoCC,BetokoAS,ReisJP,etal.Coffeeandtea\\\\nconsumptionintheearlyadultlifespanandleftventricular\\\\nfunctioninmiddleage:theCARDIAstudy. ESCHeartFail .\\\\n2020;7(4):1510-1519.doi:10.1002/ehf2.12684\\\\n34. BodarV,ChenJ,GazianoJM,AlbertC,Djouss\\\\u00e9L.Coffee\\\\nconsumptionandriskofatrialfibrillationinthePhysicians\\\\u2019\\\\nHealthStudy. JAmHeartAssoc .2019;8(15):e011346.\\\\ndoi:10.1161/JAHA.118.011346\\\\n35. ChengM,HuZ,LuX,HuangJ,GuD.Caffeineintakeandatrial\\\\nfibrillationincidence:doseresponsemeta-analysisof\\\\nprospectivecohortstudies. CanJCardiol .2014;30(4):448-454.\\\\ndoi:10.1016/j.cjca.2013.12.026\\\\n36. HabauzitV,MorandC.Evidenceforaprotectiveeffectof\\\\npolyphenols-containingfoodsoncardiovascularhealth:an\\\\nupdateforclinicians. TherAdvChronicDis .2012;3(2):87-106.\\\\ndoi:10.1177/2040622311430006\\\\n37. Ali-Hassan-SayeghS,MirhosseiniSJ,RezaeisadrabadiM,etal.\\\\nAntioxidantsupplementationsforpreventionofatrial\\\\nfibrillationaftercardiacsurgery:anupdatedcomprehensive\\\\nsystematicreviewandmeta-analysisof23randomized\\\\ncontrolledtrials. InteractCardiovascThoracSurg .\\\\n2014;18(5):646-654.doi:10.1093/icvts/ivu020\\\\n38. DingM,SatijaA,BhupathirajuSN,etal.Associationofcoffee\\\\nconsumptionwithtotalandcause-specificmortalityin3large\\\\nprospectivecohorts. Circulation.2015;132(24):2305-2315.\\\\ndoi:10.1161/CIRCULATIONAHA.115.017341\\\\n39. Lopez-GarciaE,vanDamRM,LiTY,Rodriguez-ArtalejoF,Hu\\\\nFB.Therelationshipofcoffeeconsumptionwithmortality. Ann\\\\nInternMed.2008;148(12):904-914.\\\\ndoi:10.7326/0003-4819-148-12-200806170-00003\\\\n40. deKoningGansJM,UiterwaalCS,vanderSchouwYT,etal.Tea\\\\nandcoffeeconsumptionandcardiovascularmorbidityand\\\\nmortality.ArteriosclerThrombVascBiol .2010;30(8):1665-1671.\\\\ndoi:10.1161/ATVBAHA.109.201939\\\\n41. AndersenLF,JacobsDRJr,CarlsenMH,BlomhoffR.\\\\nConsumptionofcoffeeisassociatedwithreducedriskofdeath\\\\nattributedtoinflammatoryandcardiovasculardiseasesinthe\\\\nIowaWomen\\\\u2019sHealthStudy. AmJClinNutr .\\\\n2006;83(5):1039-1046.doi:10.1093/ajcn/83.5.1039\\\\n42. KleemolaP,JousilahtiP,PietinenP,VartiainenE,TuomilehtoJ.\\\\nCoffeeconsumptionandtheriskofcoronaryheartdiseaseand\\\\ndeath.ArchInternMed .2000;160(22):3393-3400.\\\\ndoi:10.1001/archinte.160.22.3393\\\\n43. KimY,JeY,GiovannucciE.Coffeeconsumptionandall-cause\\\\nandcause-specificmortality:ameta-analysisbypotential\\\\nmodifiers.EurJEpidemiol .2019;34(8):731-752.\\\\ndoi:10.1007/s10654-019-00524-3\\\\nVolume23,Number2,Summer2023 157 Coffee Consumption and Cardiovascular Health\\\\nThis article meets the Accreditation Council for Graduate Medical Education and the American Board of Medical\\\\nSpecialties Maintenance of Certi\\\\ufb01cation competencies for Patient Care and Medical Knowledge.\\\\n\\\\u00a92023 by the author(s); licensee Ochsner Journal, Ochsner Clinic Foundation, New Orleans, LA. This article is an open\\\\naccess article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license\\\\n(creativecommons.org/licenses/by/4.0/legalcode) that permits unrestricted use, distribution, and reproduction in\\\\nany medium, provided the original author(s) and source are credited.\\\\n158 OchsnerJournal\", \"chunk_size\": 8077, \"chunk_index\": 1, \"cut_type\": \"sentence_cut\", \"id\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"color\": \"#801212\"}, {\"name\": \"diabetes mellitus\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A group of diseases that affect how the body uses blood sugar (glucose).\", \"id\": \"d5371db8-e657-54e2-9d0b-010b5d066f6b\", \"color\": \"#f47710\"}, {\"name\": \"condition\", \"type\": \"EntityType\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"condition\", \"id\": \"d9247316-841a-5a85-98ae-313571381f36\", \"color\": \"#6510f4\"}, {\"name\": \"coronary artery risk development in young adults study 2020\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"A study that analyzed the impact of coffee consumption on cardiovascular health, published by the European Society of Cardiology.\", \"id\": \"ca1b7cbb-f22b-507b-a9e5-7d1489f0f346\", \"color\": \"#f47710\"}, {\"name\": \"mendoza, mf\", \"type\": \"Entity\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"name\"]}, \"belongs_to_set\": null, \"description\": \"Author of the study discussing coffee consumption and cardiovascular health.\", \"id\": \"e1031297-63ce-5f88-bafc-b457dcb264b3\", \"color\": \"#f47710\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"This study investigates the link between regular coffee intake and overall, cardiovascular, and cancer mortality in an adult population in Spain, evaluating both the quantity and type of coffee consumed. Using baseline coffee consumption data from 1567 participants over 18 years, the research reveals that drinking coffee \\\\u2014 particularly caffeinated coffee \\\\u2014 correlates with a reduced risk of all-cause and cancer mortality. Specifically, consuming one cup or less per day and more than one cup per day yielded hazard ratios (HR) of 0.73 (95% CI: 0.56-0.97) and 0.56 (95% CI: 0.41-0.77), respectively. More than one cup daily was linked to lower cancer mortality (HR 0.41, 95% CI 0.20-0.86). Only the total caffeinated coffee intake was significantly associated with lower mortality rates. Overall, moderate consumption of coffee (1-6.5 cups/day) appears beneficial for longevity, while no significant relationship was identified between coffee consumption and cardiovascular disease (CVD) mortality.\", \"id\": \"72a5d6f9-794b-56bd-ab79-2964d6458f6b\", \"color\": \"#1077f4\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"This study analyzes the socio-demographic and lifestyle factors associated with coffee consumption among 1,567 participants aged 20 and older in Spain. It reveals significant differences in coffee consumption based on education level and smoking status, while age, waist circumference, and body mass index show varied relationships. Importantly, higher coffee intake correlates with lower mortality rates from both cardiovascular diseases (CVD) and cancer over 18 years. Specifically, more than one cup of coffee daily is linked to a 56% reduced risk of all-cause mortality and a notable inverse association with cancer mortality.\", \"id\": \"485b6646-d640-50f0-8c71-511670ee9adc\", \"color\": \"#1077f4\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"This study indicates an inverse relationship between initial coffee intake and overall as well as cancer mortality in a Mediterranean adult cohort after 18 years. Compared to non-consumers, having one or fewer coffee cups daily correlated with a 27% decrease in all-cause mortality, while consuming 2-6.5 cups per day linked to a 44% reduction. A noteworthy 59% drop in cancer mortality was noted for those drinking over one cup daily. The protective effects were primarily associated with caffeinated coffee. The findings align with previous meta-analyses yet are distinctive as this is the first investigation focusing on a Mediterranean adult population. Limitations include insufficient data on decaffeinated coffee and small sample size; strengths comprise a well-defined population and reliable baseline data collection. In conclusion, moderate coffee consumption, especially caffeinated, may enhance longevity and combat cancer mortality, suggesting its endorsement in a healthy Mediterranean lifestyle.\", \"id\": \"62937392-218c-5131-bda4-541c493d007a\", \"color\": \"#1077f4\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Coffee Consumption and Health Outcomes\", \"id\": \"595b2594-6c18-51e0-a3c1-c25707ed9c12\", \"color\": \"#1077f4\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Impact of Coffee Consumption on Cardiovascular Health\", \"id\": \"f333ac7c-ead6-56cf-890b-d3bada48e89d\", \"color\": \"#1077f4\"}, {\"name\": \"\", \"type\": \"TextSummary\", \"ontology_valid\": false, \"version\": 1, \"topological_rank\": 0, \"metadata\": {\"index_fields\": [\"text\"]}, \"belongs_to_set\": null, \"text\": \"Moderate coffee intake is linked to various health benefits, including a reduction in all-cause and cardiovascular-related mortality, lower hypertension, improved cholesterol levels, decreased risk of heart failure, and reduced incidence of atrial fibrillation. Despite concerns about coffee contributing to coronary heart disease, recent studies show no significant association, although the outcomes vary based on demographics, sex, and genetic factors. Coffee\\'s beneficial effects may stem from its antioxidant and anti-inflammatory compounds, suggesting it can be part of a wholesome lifestyle. Further research is necessary to fully understand the mechanisms behind these health benefits and to define optimal consumption levels.\", \"id\": \"09514d2d-d209-52e4-bd93-a248ae2add12\", \"color\": \"#1077f4\"}];\\n            var links = [{\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"73686bd4-8bf6-539f-bfb6-7005fa5cf8c1\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"426b61ad-65cd-5d67-8cab-afcc8c6d098f\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"06ac33ad-00d4-5de5-b27a-8569e42be8a7\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"ad852bf1-e0a7-5eed-9f7a-1fff2ba66712\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"d9df2414-2628-5d0c-b448-aa2fcdd573e1\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"4c8196cb-690c-596a-b1d2-190773bcfc0d\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"03d5df54-a749-5694-931b-20d6c69fac62\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"5de4513d-9a64-58e9-b4ea-d68796890340\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"37e4fcd4-801c-5748-9088-125fe43fa22e\", \"relation\": \"is_part_of\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"03cd983d-6f20-5db8-9a09-0bb9b986753d\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"99108d40-2e45-51f8-bda7-724b8a85a88d\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"d4b3865e-b1ee-5600-b850-09fd81f3417c\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"6db389ac-54c5-5955-95c7-fa3adc77efcb\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"ebd7537b-8a59-57dc-8908-d7bc7d092f25\", \"relation\": \"contains\"}, {\"source\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"target\": \"ef3f0655-d56c-59bc-a390-0a97f6c46bdd\", \"relation\": \"contains\"}, {\"source\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"target\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"relation\": \"is_a\"}, {\"source\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"contributes_to\"}, {\"source\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"target\": \"c5472471-fc1f-5934-b56a-40806cdb1dfd\", \"relation\": \"is_a\"}, {\"source\": \"73686bd4-8bf6-539f-bfb6-7005fa5cf8c1\", \"target\": \"02cad045-645c-5a93-98f5-17d79b3549dc\", \"relation\": \"is_a\"}, {\"source\": \"426b61ad-65cd-5d67-8cab-afcc8c6d098f\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"06ac33ad-00d4-5de5-b27a-8569e42be8a7\", \"target\": \"19dd7d4d-a966-5ed5-82a0-6ae377761a29\", \"relation\": \"is_a\"}, {\"source\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"target\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"relation\": \"is_a\"}, {\"source\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"contributes_to\"}, {\"source\": \"ad852bf1-e0a7-5eed-9f7a-1fff2ba66712\", \"target\": \"4fb3e11c-e7e6-522b-a299-500cdd695731\", \"relation\": \"is_a\"}, {\"source\": \"ad852bf1-e0a7-5eed-9f7a-1fff2ba66712\", \"target\": \"03cd983d-6f20-5db8-9a09-0bb9b986753d\", \"relation\": \"exhibit\"}, {\"source\": \"d9df2414-2628-5d0c-b448-aa2fcdd573e1\", \"target\": \"2424d934-8e73-5ce0-95d4-29f9cd4dfa28\", \"relation\": \"is_a\"}, {\"source\": \"d9df2414-2628-5d0c-b448-aa2fcdd573e1\", \"target\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"relation\": \"used_in\"}, {\"source\": \"4c8196cb-690c-596a-b1d2-190773bcfc0d\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"03d5df54-a749-5694-931b-20d6c69fac62\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"5de4513d-9a64-58e9-b4ea-d68796890340\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"3c4c0ff9-f8fb-58ca-945c-6fc820ee0c0d\", \"relation\": \"is_a\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"426b61ad-65cd-5d67-8cab-afcc8c6d098f\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"5de4513d-9a64-58e9-b4ea-d68796890340\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"03d5df54-a749-5694-931b-20d6c69fac62\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"99108d40-2e45-51f8-bda7-724b8a85a88d\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"6db389ac-54c5-5955-95c7-fa3adc77efcb\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"ebd7537b-8a59-57dc-8908-d7bc7d092f25\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"4c8196cb-690c-596a-b1d2-190773bcfc0d\", \"relation\": \"authored_by\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"relation\": \"data_from\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"73686bd4-8bf6-539f-bfb6-7005fa5cf8c1\", \"relation\": \"adheres_to\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"relation\": \"studies_relationship\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"relation\": \"studies_relationship\"}, {\"source\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"target\": \"ef3f0655-d56c-59bc-a390-0a97f6c46bdd\", \"relation\": \"cites\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"15209a1f-a093-561d-a5bb-47e12a94b836\", \"relation\": \"is_a\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"associated_with\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"ad852bf1-e0a7-5eed-9f7a-1fff2ba66712\", \"relation\": \"contains\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"4fc5509c-8300-53d5-b266-186fc6027de6\", \"relation\": \"includes\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"83776331-108c-59f1-be51-d91819f62bf9\", \"relation\": \"includes\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"relation\": \"influences\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"relation\": \"associated_with\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"relation\": \"associated_with\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"7772ab5b-e0ed-5eab-801a-c36740862804\", \"relation\": \"associated_with\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"6ec740cf-ccfb-57ba-8489-41caf3605aa6\", \"relation\": \"inconsistent_association_with\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"7073fe83-625c-597f-8497-9da0fc02510b\", \"relation\": \"published_in\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"relation\": \"affects\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"affects\"}, {\"source\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"target\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"relation\": \"contains\"}, {\"source\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"target\": \"96c859b6-e408-58e5-9be8-92bb84908325\", \"relation\": \"is_a\"}, {\"source\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"target\": \"06ac33ad-00d4-5de5-b27a-8569e42be8a7\", \"relation\": \"conducted_in\"}, {\"source\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"assesses\"}, {\"source\": \"03cd983d-6f20-5db8-9a09-0bb9b986753d\", \"target\": \"732c9c8b-0d81-5f38-9e7c-a8b7a6ebc692\", \"relation\": \"is_a\"}, {\"source\": \"99108d40-2e45-51f8-bda7-724b8a85a88d\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"d4b3865e-b1ee-5600-b850-09fd81f3417c\", \"target\": \"8a61bd85-0186-59fb-8d5d-571ad63e34a0\", \"relation\": \"is_a\"}, {\"source\": \"d4b3865e-b1ee-5600-b850-09fd81f3417c\", \"target\": \"df1acf2f-23c6-5127-83c3-ab4b796c037d\", \"relation\": \"applied_in\"}, {\"source\": \"6db389ac-54c5-5955-95c7-fa3adc77efcb\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"ebd7537b-8a59-57dc-8908-d7bc7d092f25\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"ef3f0655-d56c-59bc-a390-0a97f6c46bdd\", \"target\": \"6b51c7bc-e83c-5160-99ef-452770420a2c\", \"relation\": \"is_a\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"c175a217-f973-5aec-b59e-bdca26ea1a26\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"8a95b2c3-8766-5f2b-944c-30a022abaa94\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"c1b07b09-a33a-5b9f-9230-3011993c5d90\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"c0b30b48-9adb-5ce2-97bc-adceb40cc5c0\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"589cdc37-861f-56ae-8499-33164a1d142c\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"229aca40-804f-5471-81d3-39872da5cec1\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"83776331-108c-59f1-be51-d91819f62bf9\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"66a2fbcc-95e5-5290-8d62-d71dd5c51128\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"96307440-5e1f-5d23-a099-8125588c67db\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"37e4fcd4-801c-5748-9088-125fe43fa22e\", \"relation\": \"is_part_of\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"5e3edbad-ec37-540b-b21b-63ab4a42c952\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"526560d9-928c-54ad-ae7d-07b4895b755b\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"12e8cf69-b899-5748-b19d-32763c395a0b\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"e6bce6b8-a790-5220-bf76-f1b3336f14c3\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"4fc5509c-8300-53d5-b266-186fc6027de6\", \"relation\": \"contains\"}, {\"source\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"target\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"relation\": \"contains\"}, {\"source\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"target\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"relation\": \"is_a\"}, {\"source\": \"c175a217-f973-5aec-b59e-bdca26ea1a26\", \"target\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"relation\": \"is_a\"}, {\"source\": \"8a95b2c3-8766-5f2b-944c-30a022abaa94\", \"target\": \"96c859b6-e408-58e5-9be8-92bb84908325\", \"relation\": \"is_a\"}, {\"source\": \"8a95b2c3-8766-5f2b-944c-30a022abaa94\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"assesses\"}, {\"source\": \"8a95b2c3-8766-5f2b-944c-30a022abaa94\", \"target\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"relation\": \"focuses_on\"}, {\"source\": \"c1b07b09-a33a-5b9f-9230-3011993c5d90\", \"target\": \"536be56d-a2ef-5caa-8b42-489997d9d5c8\", \"relation\": \"is_a\"}, {\"source\": \"c0b30b48-9adb-5ce2-97bc-adceb40cc5c0\", \"target\": \"536be56d-a2ef-5caa-8b42-489997d9d5c8\", \"relation\": \"is_a\"}, {\"source\": \"589cdc37-861f-56ae-8499-33164a1d142c\", \"target\": \"262b23f9-b2a1-55c9-bbe7-2d48f3e7cff9\", \"relation\": \"is_a\"}, {\"source\": \"589cdc37-861f-56ae-8499-33164a1d142c\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"analyzed_in\"}, {\"source\": \"589cdc37-861f-56ae-8499-33164a1d142c\", \"target\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"relation\": \"represents\"}, {\"source\": \"229aca40-804f-5471-81d3-39872da5cec1\", \"target\": \"262b23f9-b2a1-55c9-bbe7-2d48f3e7cff9\", \"relation\": \"is_a\"}, {\"source\": \"229aca40-804f-5471-81d3-39872da5cec1\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"analyzed_in\"}, {\"source\": \"229aca40-804f-5471-81d3-39872da5cec1\", \"target\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"relation\": \"represents\"}, {\"source\": \"83776331-108c-59f1-be51-d91819f62bf9\", \"target\": \"71ae3ac4-8c4d-5f66-a7fb-46360085350d\", \"relation\": \"is_a\"}, {\"source\": \"83776331-108c-59f1-be51-d91819f62bf9\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"associated_with\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"71ae3ac4-8c4d-5f66-a7fb-46360085350d\", \"relation\": \"is_a\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"5e3edbad-ec37-540b-b21b-63ab4a42c952\", \"relation\": \"reports\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"c175a217-f973-5aec-b59e-bdca26ea1a26\", \"relation\": \"reports\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"relation\": \"reports\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"c0b30b48-9adb-5ce2-97bc-adceb40cc5c0\", \"relation\": \"assesses\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"c1b07b09-a33a-5b9f-9230-3011993c5d90\", \"relation\": \"assesses\"}, {\"source\": \"b0af28e9-a215-5466-b063-d00c1fb8089b\", \"target\": \"96307440-5e1f-5d23-a099-8125588c67db\", \"relation\": \"assesses\"}, {\"source\": \"96307440-5e1f-5d23-a099-8125588c67db\", \"target\": \"536be56d-a2ef-5caa-8b42-489997d9d5c8\", \"relation\": \"is_a\"}, {\"source\": \"5e3edbad-ec37-540b-b21b-63ab4a42c952\", \"target\": \"907ac8fb-f806-5119-a653-9099bf800f95\", \"relation\": \"is_a\"}, {\"source\": \"12e8cf69-b899-5748-b19d-32763c395a0b\", \"target\": \"262b23f9-b2a1-55c9-bbe7-2d48f3e7cff9\", \"relation\": \"is_a\"}, {\"source\": \"12e8cf69-b899-5748-b19d-32763c395a0b\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"analyzed_in\"}, {\"source\": \"12e8cf69-b899-5748-b19d-32763c395a0b\", \"target\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"relation\": \"represents\"}, {\"source\": \"4fc5509c-8300-53d5-b266-186fc6027de6\", \"target\": \"71ae3ac4-8c4d-5f66-a7fb-46360085350d\", \"relation\": \"is_a\"}, {\"source\": \"4fc5509c-8300-53d5-b266-186fc6027de6\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"associated_with\"}, {\"source\": \"f594d692-b0d8-5ed5-9580-4fc82b508343\", \"target\": \"f45cdf53-a433-54a4-8122-7f90d2cdd32e\", \"relation\": \"is_a\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"9b0132a6-2fa9-50d4-9786-7856610c9e31\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"37e4fcd4-801c-5748-9088-125fe43fa22e\", \"relation\": \"is_part_of\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"0ca0ad29-9f79-5d2c-b6b6-325df830ed1c\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"c78c1da9-aa59-509c-8764-e7988ba0d4cc\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"a2c4702d-8e81-531c-8ab8-2a147b4c7cc3\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"bd749f32-5faa-53fc-8dd0-fc1c70e9ef31\", \"relation\": \"contains\"}, {\"source\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"target\": \"b2a10138-f686-5689-b9ba-c485572a90d0\", \"relation\": \"contains\"}, {\"source\": \"9b0132a6-2fa9-50d4-9786-7856610c9e31\", \"target\": \"3d896feb-144d-51bd-9aeb-afe8e845a3e4\", \"relation\": \"is_a\"}, {\"source\": \"0ca0ad29-9f79-5d2c-b6b6-325df830ed1c\", \"target\": \"addbc55c-7f21-5cae-86c4-8cb0de93452b\", \"relation\": \"is_a\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"931754d5-ca60-5ed3-a7ea-e569447223c6\", \"relation\": \"is_a\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"a2c4702d-8e81-531c-8ab8-2a147b4c7cc3\", \"relation\": \"studied_in\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"b2a10138-f686-5689-b9ba-c485572a90d0\", \"relation\": \"investigates\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"bd749f32-5faa-53fc-8dd0-fc1c70e9ef31\", \"relation\": \"investigates\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"9b0132a6-2fa9-50d4-9786-7856610c9e31\", \"relation\": \"investigates\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"c78c1da9-aa59-509c-8764-e7988ba0d4cc\", \"relation\": \"contains\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"0ca0ad29-9f79-5d2c-b6b6-325df830ed1c\", \"relation\": \"contains\"}, {\"source\": \"aaf7bbae-973d-5066-ab30-c84fe06f3335\", \"target\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"relation\": \"contains\"}, {\"source\": \"c78c1da9-aa59-509c-8764-e7988ba0d4cc\", \"target\": \"addbc55c-7f21-5cae-86c4-8cb0de93452b\", \"relation\": \"is_a\"}, {\"source\": \"a2c4702d-8e81-531c-8ab8-2a147b4c7cc3\", \"target\": \"66d00649-f9eb-5eec-ac58-b91bb0662ffd\", \"relation\": \"is_a\"}, {\"source\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"target\": \"addbc55c-7f21-5cae-86c4-8cb0de93452b\", \"relation\": \"is_a\"}, {\"source\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"target\": \"b2a10138-f686-5689-b9ba-c485572a90d0\", \"relation\": \"may_reduce\"}, {\"source\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"target\": \"bd749f32-5faa-53fc-8dd0-fc1c70e9ef31\", \"relation\": \"may_reduce\"}, {\"source\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"target\": \"9b0132a6-2fa9-50d4-9786-7856610c9e31\", \"relation\": \"may_reduce\"}, {\"source\": \"bd749f32-5faa-53fc-8dd0-fc1c70e9ef31\", \"target\": \"3d896feb-144d-51bd-9aeb-afe8e845a3e4\", \"relation\": \"is_a\"}, {\"source\": \"b2a10138-f686-5689-b9ba-c485572a90d0\", \"target\": \"3d896feb-144d-51bd-9aeb-afe8e845a3e4\", \"relation\": \"is_a\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"3ba13355-e09c-5af5-94ba-c4c49856e595\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"832d2fd5-626b-5436-a2db-af7ee6722c27\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"280404f4-d1d4-5053-afdf-aee728a4ac40\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"86bc15f8-dde3-5a97-bffa-83b1f68a2636\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"aecdfa63-2116-580d-b26b-12b4a2fd2ab7\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"685dea78-218d-5b8e-9ed3-270da5257b2c\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"a34476ef-9d9e-5323-8d2c-b3377401be07\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"8097f2a6-d14e-5e0f-b6c5-53e8e55839b5\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"0119136a-8473-5b1d-9c19-231a37583250\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"53f1ca8e-f701-5c29-8967-db9967174aed\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"ecdcfbf3-cadf-580c-9490-b3ad26964e9b\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"1c41f80f-f723-54cb-8991-1d4913a82b73\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"a106fc02-1ada-5972-a24f-6f5f23592c4f\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"37e4fcd4-801c-5748-9088-125fe43fa22e\", \"relation\": \"is_part_of\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"435650bb-100e-59c2-96e4-f3d403db5f3d\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"46a295a5-5ac7-5fb9-8f34-be9738c31358\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"eaf6ed9d-b3a5-50fe-9b53-40470f11dc3c\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"9cae226b-7048-50c4-9162-461438c0b9f0\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"20851b25-35e0-53b6-a2dc-46aa2b0c736b\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"46a52c54-a100-5e31-be75-9c91c06f9198\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"0fc618e7-1917-5c7c-b74e-28bf71640010\", \"relation\": \"contains\"}, {\"source\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"target\": \"b7d3f418-8d8c-534d-88ce-4d20046149af\", \"relation\": \"contains\"}, {\"source\": \"3ba13355-e09c-5af5-94ba-c4c49856e595\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"3ba13355-e09c-5af5-94ba-c4c49856e595\", \"target\": \"685dea78-218d-5b8e-9ed3-270da5257b2c\", \"relation\": \"cites\"}, {\"source\": \"832d2fd5-626b-5436-a2db-af7ee6722c27\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"280404f4-d1d4-5053-afdf-aee728a4ac40\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"86bc15f8-dde3-5a97-bffa-83b1f68a2636\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"86bc15f8-dde3-5a97-bffa-83b1f68a2636\", \"target\": \"ecdcfbf3-cadf-580c-9490-b3ad26964e9b\", \"relation\": \"cites\"}, {\"source\": \"aecdfa63-2116-580d-b26b-12b4a2fd2ab7\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"aecdfa63-2116-580d-b26b-12b4a2fd2ab7\", \"target\": \"a106fc02-1ada-5972-a24f-6f5f23592c4f\", \"relation\": \"cites\"}, {\"source\": \"685dea78-218d-5b8e-9ed3-270da5257b2c\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"a34476ef-9d9e-5323-8d2c-b3377401be07\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"a34476ef-9d9e-5323-8d2c-b3377401be07\", \"target\": \"8097f2a6-d14e-5e0f-b6c5-53e8e55839b5\", \"relation\": \"cites\"}, {\"source\": \"8097f2a6-d14e-5e0f-b6c5-53e8e55839b5\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"0119136a-8473-5b1d-9c19-231a37583250\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"0119136a-8473-5b1d-9c19-231a37583250\", \"target\": \"0fc618e7-1917-5c7c-b74e-28bf71640010\", \"relation\": \"cites\"}, {\"source\": \"53f1ca8e-f701-5c29-8967-db9967174aed\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"53f1ca8e-f701-5c29-8967-db9967174aed\", \"target\": \"ecdcfbf3-cadf-580c-9490-b3ad26964e9b\", \"relation\": \"cites\"}, {\"source\": \"ecdcfbf3-cadf-580c-9490-b3ad26964e9b\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"1c41f80f-f723-54cb-8991-1d4913a82b73\", \"target\": \"90cb1fed-d3a3-51c4-bf2d-467bce3d40a3\", \"relation\": \"is_a\"}, {\"source\": \"a106fc02-1ada-5972-a24f-6f5f23592c4f\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"435650bb-100e-59c2-96e4-f3d403db5f3d\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"435650bb-100e-59c2-96e4-f3d403db5f3d\", \"target\": \"a34476ef-9d9e-5323-8d2c-b3377401be07\", \"relation\": \"cites\"}, {\"source\": \"46a295a5-5ac7-5fb9-8f34-be9738c31358\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"46a295a5-5ac7-5fb9-8f34-be9738c31358\", \"target\": \"280404f4-d1d4-5053-afdf-aee728a4ac40\", \"relation\": \"cites\"}, {\"source\": \"eaf6ed9d-b3a5-50fe-9b53-40470f11dc3c\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"9cae226b-7048-50c4-9162-461438c0b9f0\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"9cae226b-7048-50c4-9162-461438c0b9f0\", \"target\": \"53f1ca8e-f701-5c29-8967-db9967174aed\", \"relation\": \"cites\"}, {\"source\": \"20851b25-35e0-53b6-a2dc-46aa2b0c736b\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"20851b25-35e0-53b6-a2dc-46aa2b0c736b\", \"target\": \"832d2fd5-626b-5436-a2db-af7ee6722c27\", \"relation\": \"cites\"}, {\"source\": \"46a52c54-a100-5e31-be75-9c91c06f9198\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"46a52c54-a100-5e31-be75-9c91c06f9198\", \"target\": \"0fc618e7-1917-5c7c-b74e-28bf71640010\", \"relation\": \"cites\"}, {\"source\": \"0fc618e7-1917-5c7c-b74e-28bf71640010\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"b7d3f418-8d8c-534d-88ce-4d20046149af\", \"target\": \"9087a189-dc41-5c03-a07c-13227250b1b5\", \"relation\": \"is_a\"}, {\"source\": \"b7d3f418-8d8c-534d-88ce-4d20046149af\", \"target\": \"eaf6ed9d-b3a5-50fe-9b53-40470f11dc3c\", \"relation\": \"cites\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"2e1cc3a7-b555-53ac-8239-1d6793d51b6e\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"d5c90c81-efa1-5a49-98d7-50e43440c18c\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"7772ab5b-e0ed-5eab-801a-c36740862804\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"9569c511-9ddc-5026-bf1e-5f8e7092558a\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"7073fe83-625c-597f-8497-9da0fc02510b\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"a2a2969f-2efa-5d9c-96f1-60b2d106641b\", \"relation\": \"is_part_of\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"6ec740cf-ccfb-57ba-8489-41caf3605aa6\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"678c66ec-12bf-50ce-8325-03731de6e10c\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"a0c86064-a0d8-5c1d-999f-a8e20ad4e784\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"f3c82751-703d-598c-9f2c-332c08ebbb1d\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"1b9533e0-f89c-5cfd-be59-d31448fff700\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"39dee7b2-b681-5c4a-96cd-8d5119bcbd7d\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"relation\": \"contains\"}, {\"source\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"target\": \"b15d8f44-a728-5257-80ed-ec1c87a507f9\", \"relation\": \"contains\"}, {\"source\": \"2e1cc3a7-b555-53ac-8239-1d6793d51b6e\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"d5c90c81-efa1-5a49-98d7-50e43440c18c\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"d5c90c81-efa1-5a49-98d7-50e43440c18c\", \"target\": \"2e1cc3a7-b555-53ac-8239-1d6793d51b6e\", \"relation\": \"contains\"}, {\"source\": \"7772ab5b-e0ed-5eab-801a-c36740862804\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"9569c511-9ddc-5026-bf1e-5f8e7092558a\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"7073fe83-625c-597f-8497-9da0fc02510b\", \"target\": \"d61d99ac-b291-5666-9748-3e80e1c8b56a\", \"relation\": \"is_a\"}, {\"source\": \"6ec740cf-ccfb-57ba-8489-41caf3605aa6\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"678c66ec-12bf-50ce-8325-03731de6e10c\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"a0c86064-a0d8-5c1d-999f-a8e20ad4e784\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"f3c82751-703d-598c-9f2c-332c08ebbb1d\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"1b9533e0-f89c-5cfd-be59-d31448fff700\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"39dee7b2-b681-5c4a-96cd-8d5119bcbd7d\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"b15d8f44-a728-5257-80ed-ec1c87a507f9\", \"target\": \"dd9713b7-dc20-5101-aad0-1c4216811147\", \"relation\": \"is_a\"}, {\"source\": \"b15d8f44-a728-5257-80ed-ec1c87a507f9\", \"target\": \"39dee7b2-b681-5c4a-96cd-8d5119bcbd7d\", \"relation\": \"influences\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"d5371db8-e657-54e2-9d0b-010b5d066f6b\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"a2a2969f-2efa-5d9c-96f1-60b2d106641b\", \"relation\": \"is_part_of\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"ca1b7cbb-f22b-507b-a9e5-7d1489f0f346\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"7772ab5b-e0ed-5eab-801a-c36740862804\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"e1031297-63ce-5f88-bafc-b457dcb264b3\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"06882468-281d-55b0-b880-06ddc6aeece2\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"794ae1c2-a7fc-5dce-a8be-cc0caf0652dc\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"9e22bd5f-12ad-58c0-9298-903b1b5cff4a\", \"relation\": \"contains\"}, {\"source\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"target\": \"9fcc966c-1c9a-5dad-9773-bef49b527261\", \"relation\": \"contains\"}, {\"source\": \"d5371db8-e657-54e2-9d0b-010b5d066f6b\", \"target\": \"d9247316-841a-5a85-98ae-313571381f36\", \"relation\": \"is_a\"}, {\"source\": \"d5371db8-e657-54e2-9d0b-010b5d066f6b\", \"target\": \"0b969dc1-ee29-5309-93cb-adc447b5385a\", \"relation\": \"affects\"}, {\"source\": \"ca1b7cbb-f22b-507b-a9e5-7d1489f0f346\", \"target\": \"96c859b6-e408-58e5-9be8-92bb84908325\", \"relation\": \"is_a\"}, {\"source\": \"ca1b7cbb-f22b-507b-a9e5-7d1489f0f346\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"published_in\"}, {\"source\": \"e1031297-63ce-5f88-bafc-b457dcb264b3\", \"target\": \"d072ba0f-e1a9-58bf-9974-e1802adc8134\", \"relation\": \"is_a\"}, {\"source\": \"e1031297-63ce-5f88-bafc-b457dcb264b3\", \"target\": \"955fc5b7-c05b-5a74-a7f2-386fabaaabe0\", \"relation\": \"authored\"}, {\"source\": \"72a5d6f9-794b-56bd-ab79-2964d6458f6b\", \"target\": \"2a744f69-ce9b-5c50-8a94-0782d00a2f42\", \"relation\": \"made_from\"}, {\"source\": \"485b6646-d640-50f0-8c71-511670ee9adc\", \"target\": \"e48510e2-585d-5ce8-be0c-edfe00527d96\", \"relation\": \"made_from\"}, {\"source\": \"62937392-218c-5131-bda4-541c493d007a\", \"target\": \"89a2b1fd-1db1-5676-ab35-9f6883a7387f\", \"relation\": \"made_from\"}, {\"source\": \"595b2594-6c18-51e0-a3c1-c25707ed9c12\", \"target\": \"d83eb568-8f08-5c10-8af0-80c0074d1567\", \"relation\": \"made_from\"}, {\"source\": \"f333ac7c-ead6-56cf-890b-d3bada48e89d\", \"target\": \"79a4336a-2621-506c-9d27-2c2ef19c625f\", \"relation\": \"made_from\"}, {\"source\": \"09514d2d-d209-52e4-bd93-a248ae2add12\", \"target\": \"8540a45c-33ef-5de3-a401-3485d5efeefa\", \"relation\": \"made_from\"}];\\n\\n            var svg = d3.select(\"svg\"),\\n                width = window.innerWidth,\\n                height = window.innerHeight;\\n\\n            var container = svg.append(\"g\");\\n\\n            var simulation = d3.forceSimulation(nodes)\\n                .force(\"link\", d3.forceLink(links).id(d => d.id).strength(0.1))\\n                .force(\"charge\", d3.forceManyBody().strength(-275))\\n                .force(\"center\", d3.forceCenter(width / 2, height / 2))\\n                .force(\"x\", d3.forceX().strength(0.1).x(width / 2))\\n                .force(\"y\", d3.forceY().strength(0.1).y(height / 2));\\n\\n            var link = container.append(\"g\")\\n                .attr(\"class\", \"links\")\\n                .selectAll(\"line\")\\n                .data(links)\\n                .enter().append(\"line\")\\n                .attr(\"stroke-width\", 2);\\n\\n            var edgeLabels = container.append(\"g\")\\n                .attr(\"class\", \"edge-labels\")\\n                .selectAll(\"text\")\\n                .data(links)\\n                .enter().append(\"text\")\\n                .attr(\"class\", \"edge-label\")\\n                .text(d => d.relation);\\n\\n            var nodeGroup = container.append(\"g\")\\n                .attr(\"class\", \"nodes\")\\n                .selectAll(\"g\")\\n                .data(nodes)\\n                .enter().append(\"g\");\\n\\n            var node = nodeGroup.append(\"circle\")\\n                .attr(\"r\", 13)\\n                .attr(\"fill\", d => d.color)\\n                .call(d3.drag()\\n                    .on(\"start\", dragstarted)\\n                    .on(\"drag\", dragged)\\n                    .on(\"end\", dragended));\\n\\n            nodeGroup.append(\"text\")\\n                .attr(\"class\", \"node-label\")\\n                .attr(\"dy\", 4)\\n                .attr(\"text-anchor\", \"middle\")\\n                .text(d => d.name);\\n\\n            node.append(\"title\").text(d => JSON.stringify(d));\\n\\n            simulation.on(\"tick\", function() {\\n                link.attr(\"x1\", d => d.source.x)\\n                    .attr(\"y1\", d => d.source.y)\\n                    .attr(\"x2\", d => d.target.x)\\n                    .attr(\"y2\", d => d.target.y);\\n\\n                edgeLabels\\n                    .attr(\"x\", d => (d.source.x + d.target.x) / 2)\\n                    .attr(\"y\", d => (d.source.y + d.target.y) / 2 - 5);\\n\\n                node.attr(\"cx\", d => d.x)\\n                    .attr(\"cy\", d => d.y);\\n\\n                nodeGroup.select(\"text\")\\n                    .attr(\"x\", d => d.x)\\n                    .attr(\"y\", d => d.y)\\n                    .attr(\"dy\", 4)\\n                    .attr(\"text-anchor\", \"middle\");\\n            });\\n\\n            svg.call(d3.zoom().on(\"zoom\", function() {\\n                container.attr(\"transform\", d3.event.transform);\\n            }));\\n\\n            function dragstarted(d) {\\n                if (!d3.event.active) simulation.alphaTarget(0.3).restart();\\n                d.fx = d.x;\\n                d.fy = d.y;\\n            }\\n\\n            function dragged(d) {\\n                d.fx = d3.event.x;\\n                d.fy = d3.event.y;\\n            }\\n\\n            function dragended(d) {\\n                if (!d3.event.active) simulation.alphaTarget(0);\\n                d.fx = null;\\n                d.fy = null;\\n            }\\n\\n            window.addEventListener(\"resize\", function() {\\n                width = window.innerWidth;\\n                height = window.innerHeight;\\n                svg.attr(\"width\", width).attr(\"height\", height);\\n                simulation.force(\"center\", d3.forceCenter(width / 2, height / 2));\\n                simulation.alpha(1).restart();\\n            });\\n        </script>\\n\\n        <svg style=\"position: fixed; bottom: 10px; right: 10px; width: 150px; height: auto; z-index: 9999;\" viewBox=\"0 0 158 44\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\">\\n            <path fill-rule=\"evenodd\" clip-rule=\"evenodd\" d=\"M11.7496 4.92654C7.83308 4.92654 4.8585 7.94279 4.8585 11.3612V14.9304C4.8585 18.3488 7.83308 21.3651 11.7496 21.3651C13.6831 21.3651 15.0217 20.8121 16.9551 19.3543C18.0458 18.5499 19.5331 18.8013 20.3263 19.9072C21.1195 21.0132 20.8717 22.5213 19.781 23.3257C17.3518 25.0851 15.0217 26.2414 11.7 26.2414C5.35425 26.2414 0 21.2646 0 14.9304V11.3612C0 4.97681 5.35425 0.0502739 11.7 0.0502739C15.0217 0.0502739 17.3518 1.2065 19.781 2.96598C20.8717 3.77032 21.1195 5.27843 20.3263 6.38439C19.5331 7.49035 18.0458 7.69144 16.9551 6.93737C15.0217 5.52979 13.6831 4.92654 11.7496 4.92654ZM35.5463 4.92654C31.7289 4.92654 28.6552 8.04333 28.6552 11.8639V14.478C28.6552 18.2986 31.7289 21.4154 35.5463 21.4154C39.3141 21.4154 42.3878 18.2986 42.3878 14.478V11.8639C42.3878 8.04333 39.3141 4.92654 35.5463 4.92654ZM23.7967 11.8639C23.7967 5.32871 29.0518 0 35.5463 0C42.0408 0 47.2463 5.32871 47.2463 11.8639V14.478C47.2463 21.0132 42.0408 26.3419 35.5463 26.3419C29.0518 26.3419 23.7967 21.0635 23.7967 14.478V11.8639ZM63.3091 5.07736C59.4917 5.07736 56.418 8.19415 56.418 12.0147C56.418 15.8353 59.4917 18.9521 63.3091 18.9521C67.1265 18.9521 70.1506 15.8856 70.1506 12.0147C70.1506 8.14388 67.0769 5.07736 63.3091 5.07736ZM51.5595 11.9645C51.5595 5.42925 56.8146 0.150814 63.3091 0.150814C66.0854 0.150814 68.5642 1.10596 70.5968 2.71463L72.4311 0.904876C73.3731 -0.0502693 74.9099 -0.0502693 75.8519 0.904876C76.7938 1.86002 76.7938 3.41841 75.8519 4.37356L73.7201 6.53521C74.5629 8.19414 75.0587 10.0542 75.0587 12.0147C75.0587 18.4997 69.8532 23.8284 63.3587 23.8284C63.3091 23.8284 63.2099 23.8284 63.1603 23.8284H58.0044C57.1616 23.8284 56.4675 24.5322 56.4675 25.3868C56.4675 26.2414 57.1616 26.9452 58.0044 26.9452H64.6476H66.7794C68.5146 26.9452 70.3489 27.4479 71.7866 28.6041C73.2739 29.8106 74.2159 31.5701 74.4142 33.7317C74.7116 37.6026 72.0345 40.2166 69.8532 41.0713L63.8048 43.7859C62.5654 44.3389 61.1277 43.7859 60.6319 42.5291C60.0866 41.2723 60.6319 39.8648 61.8714 39.3118L68.0188 36.5972C68.0684 36.5972 68.118 36.5469 68.1675 36.5469C68.4154 36.4463 68.8616 36.1447 69.2087 35.6923C69.5061 35.2398 69.7044 34.7371 69.6548 34.1339C69.6053 33.229 69.2582 32.7263 68.8616 32.4247C68.4154 32.0728 67.7214 31.8214 66.8786 31.8214H58.2027C58.1531 31.8214 58.1531 31.8214 58.1035 31.8214H58.054C54.534 31.8214 51.6586 28.956 51.6586 25.3868C51.6586 23.0743 52.8485 21.0635 54.6828 19.9072C52.6997 17.7959 51.5595 15.031 51.5595 11.9645ZM90.8736 5.07736C87.0562 5.07736 83.9824 8.19415 83.9824 12.0147V23.9289C83.9824 25.2862 82.8917 26.3922 81.5532 26.3922C80.2146 26.3922 79.1239 25.2862 79.1239 23.9289V11.9645C79.1239 5.42925 84.379 0.150814 90.824 0.150814C97.2689 0.150814 102.524 5.42925 102.524 11.9645V23.8786C102.524 25.2359 101.433 26.3419 100.095 26.3419C98.7562 26.3419 97.6655 25.2359 97.6655 23.8786V11.9645C97.7647 8.14387 94.6414 5.07736 90.8736 5.07736ZM119.43 5.07736C115.513 5.07736 112.39 8.24441 112.39 12.065V14.5785C112.39 18.4494 115.513 21.5662 119.43 21.5662C120.768 21.5662 122.057 21.164 123.098 20.5105C124.238 19.8067 125.726 20.1586 126.42 21.3148C127.114 22.4711 126.767 23.9792 125.627 24.683C123.842 25.7889 121.71 26.4425 119.43 26.4425C112.885 26.4425 107.581 21.1137 107.581 14.5785V12.065C107.581 5.47952 112.935 0.201088 119.43 0.201088C125.032 0.201088 129.692 4.07194 130.931 9.3001L131.427 11.3612L121.115 15.584C119.876 16.0867 118.488 15.4834 117.942 14.2266C117.447 12.9699 118.041 11.5623 119.281 11.0596L125.478 8.54604C124.238 6.43466 122.008 5.07736 119.43 5.07736ZM146.003 5.07736C142.086 5.07736 138.963 8.24441 138.963 12.065V14.5785C138.963 18.4494 142.086 21.5662 146.003 21.5662C147.341 21.5662 148.63 21.164 149.671 20.5105C150.217 20.1586 150.663 19.8067 151.109 19.304C152.001 18.2986 153.538 18.2483 154.53 19.2034C155.521 20.1083 155.571 21.6667 154.629 22.6721C153.935 23.4262 153.092 24.13 152.2 24.683C150.415 25.7889 148.283 26.4425 146.003 26.4425C139.458 26.4425 134.154 21.1137 134.154 14.5785V12.065C134.154 5.47952 139.508 0.201088 146.003 0.201088C151.605 0.201088 156.265 4.07194 157.504 9.3001L158 11.3612L147.688 15.584C146.449 16.0867 145.061 15.4834 144.515 14.2266C144.019 12.9699 144.614 11.5623 145.854 11.0596L152.051 8.54604C150.762 6.43466 148.58 5.07736 146.003 5.07736Z\" fill=\"white\"/>\\n        </svg>\\n    </body>\\n    </html>\\n    '"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from cognee.api.v1.visualize import visualize_graph\n",
    "await visualize_graph()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ff39326921b75273",
   "metadata": {},
   "source": [
    "## Understanding the Results\n",
    "\n",
    "The demonstration above shows how ontologies enhance our analysis by:\n",
    "\n",
    "1. **Making Connections**: \n",
    "   - Linking related medical concepts even when not explicitly stated\n",
    "   - Identifying relationships between symptoms, diseases, and risk factors\n",
    "\n",
    "2. **Standardizing Terms**: \n",
    "   - Unifying different ways of referring to the same medical condition\n",
    "   - Ensuring consistent terminology across documents\n",
    "\n",
    "3. **Enabling Inference**: \n",
    "   - Drawing conclusions based on ontological relationships\n",
    "   - Discovering implicit connections in the data\n",
    "\n",
    "## Next Steps\n",
    "\n",
    "To learn more about Cognee and ontologies:\n",
    "1. Check out the [Cognee documentation](https://docs.cognee.ai/)\n",
    "2. Explore more examples in the `examples` directory\n",
    "3. Try creating your own domain-specific ontology\n",
    "\n",
    "Remember to:\n",
    "- Place your scientific papers in the appropriate directory\n",
    "- Update the ontology path to point to your .owl file\n",
    "- Replace the API key with your own OpenAI key"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8d2a0fe555a7bc0f",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}