{
  "title": "Open Data Library — drjeremytabernero.org",
  "description": "A hand-curated catalog of free, downloadable medical, pharma, and health-science databases. Every entry links to the official source.",
  "source": "https://drjeremytabernero.org/data/",
  "license": "Catalog: CC BY 4.0. Each dataset carries its own license (see the license field).",
  "count": 14,
  "datasets": [
    {
      "id": "openfda",
      "name": "openFDA",
      "maintainer": "U.S. Food & Drug Administration",
      "domain": "Drugs & safety",
      "summary": "FDA public data as JSON APIs and bulk downloads: drug adverse-event reports (FAERS), drug labels, recalls and enforcement actions, device adverse events, and NDC product listings.",
      "formats": "JSON API; bulk JSON (zipped)",
      "size": "~GBs per endpoint (adverse events are the big one)",
      "license": "Public domain (CC0)",
      "updated": "Regularly (endpoint-dependent)",
      "access": "direct download",
      "url": "https://open.fda.gov/",
      "download_url": "https://open.fda.gov/apis/downloads/"
    },
    {
      "id": "clinicaltrials-gov",
      "name": "ClinicalTrials.gov",
      "maintainer": "U.S. National Library of Medicine",
      "domain": "Clinical trials",
      "summary": "The registry and results database of clinical studies conducted around the world — protocols, arms, outcomes, and posted results. Full API (v2) plus complete bulk download of every study record.",
      "formats": "REST API (JSON); bulk JSON/CSV",
      "size": "~500k+ study records",
      "license": "Public domain (U.S. Government work); attribution requested",
      "updated": "Daily",
      "access": "direct download",
      "url": "https://clinicaltrials.gov/",
      "download_url": "https://clinicaltrials.gov/data-api/about-api"
    },
    {
      "id": "dailymed",
      "name": "DailyMed (SPL drug labels)",
      "maintainer": "U.S. National Library of Medicine",
      "domain": "Drugs & safety",
      "summary": "The current FDA label (Structured Product Labeling) for essentially every marketed drug in the U.S. — full prescribing information as structured XML, downloadable in bulk.",
      "formats": "XML (SPL); bulk ZIP releases; REST API",
      "size": "~145k+ labels; multi-GB in bulk",
      "license": "Public domain",
      "updated": "Daily",
      "access": "direct download",
      "url": "https://dailymed.nlm.nih.gov/dailymed/",
      "download_url": "https://dailymed.nlm.nih.gov/dailymed/spl-resources-all-drug-labels.cfm"
    },
    {
      "id": "orange-book",
      "name": "FDA Orange Book data files",
      "maintainer": "U.S. Food & Drug Administration",
      "domain": "Drugs & safety",
      "summary": "Approved drug products with therapeutic-equivalence evaluations — the authoritative list behind generic substitution, plus patent and exclusivity data, as plain downloadable data files.",
      "formats": "TXT (delimited) in ZIP",
      "size": "~MBs",
      "license": "Public domain",
      "updated": "Monthly",
      "access": "direct download",
      "url": "https://www.fda.gov/drugs/drug-approvals-and-databases/approved-drug-products-therapeutic-equivalence-evaluations-orange-book",
      "download_url": "https://www.fda.gov/drugs/drug-approvals-and-databases/orange-book-data-files"
    },
    {
      "id": "cdc-wonder",
      "name": "CDC WONDER",
      "maintainer": "U.S. Centers for Disease Control and Prevention",
      "domain": "Population health",
      "summary": "Query-and-export access to CDC’s epidemiologic datasets: underlying-cause-of-death mortality, natality, cancer statistics, vaccinations, and more, exportable as delimited text.",
      "formats": "web query → TSV export; API (XML)",
      "size": "Query-sized slices of very large collections",
      "license": "Public domain (data-use restrictions on small cells)",
      "updated": "Dataset-dependent (mortality: annually + provisional)",
      "access": "direct download",
      "url": "https://wonder.cdc.gov/",
      "download_url": ""
    },
    {
      "id": "nhanes",
      "name": "NHANES",
      "maintainer": "CDC / National Center for Health Statistics",
      "domain": "Population health",
      "summary": "The National Health and Nutrition Examination Survey — interviews, physical exams, and lab measurements on a representative sample of the U.S. population, in continuous cycles since 1999.",
      "formats": "SAS transport (.XPT); CSV (some cycles)",
      "size": "~MBs per cycle component",
      "license": "Public domain",
      "updated": "Biennial cycles",
      "access": "direct download",
      "url": "https://wwwn.cdc.gov/nchs/nhanes/",
      "download_url": ""
    },
    {
      "id": "who-gho",
      "name": "WHO Global Health Observatory",
      "maintainer": "World Health Organization",
      "domain": "Population health",
      "summary": "WHO’s repository of health indicators for its member states — life expectancy, disease burden, immunization coverage, health-system metrics — via an open OData API and CSV export.",
      "formats": "OData API (JSON); CSV export",
      "size": "~2k+ indicators × 190+ countries",
      "license": "CC BY-NC-SA 3.0 IGO",
      "updated": "Rolling",
      "access": "direct download",
      "url": "https://www.who.int/data/gho",
      "download_url": "https://www.who.int/data/gho/info/gho-odata-api"
    },
    {
      "id": "cms-open-payments",
      "name": "CMS Open Payments",
      "maintainer": "U.S. Centers for Medicare & Medicaid Services",
      "domain": "Payments & policy",
      "summary": "Every payment and transfer of value from drug and device companies to U.S. physicians and teaching hospitals, reported under the Sunshine Act — searchable and downloadable in full.",
      "formats": "CSV (bulk, by program year); API",
      "size": "~GBs per program year",
      "license": "Public domain",
      "updated": "Annually (with refreshes)",
      "access": "direct download",
      "url": "https://openpaymentsdata.cms.gov/",
      "download_url": "https://www.cms.gov/priorities/key-initiatives/open-payments/data/dataset-downloads"
    },
    {
      "id": "data-cms-gov",
      "name": "data.CMS.gov (Medicare utilization & providers)",
      "maintainer": "U.S. Centers for Medicare & Medicaid Services",
      "domain": "Payments & policy",
      "summary": "CMS program data: Medicare utilization and payment by provider and service, hospital cost reports, provider enrollment, and more — the raw material of U.S. health-policy analysis.",
      "formats": "CSV; API (JSON)",
      "size": "~MBs to ~GBs per dataset",
      "license": "Public domain",
      "updated": "Dataset-dependent",
      "access": "direct download",
      "url": "https://data.cms.gov/",
      "download_url": ""
    },
    {
      "id": "pubmed-baseline",
      "name": "PubMed/MEDLINE annual baseline",
      "maintainer": "U.S. National Library of Medicine",
      "domain": "Literature",
      "summary": "The complete PubMed citation database — 38M+ biomedical citations and abstracts with MeSH indexing — released annually as bulk XML, with daily update files.",
      "formats": "XML (gzipped, FTP/HTTPS)",
      "size": "~40+ GB compressed",
      "license": "Free to download; NLM terms apply to some abstract text",
      "updated": "Annual baseline + daily updates",
      "access": "direct download",
      "url": "https://pubmed.ncbi.nlm.nih.gov/download/",
      "download_url": ""
    },
    {
      "id": "physionet-mimic",
      "name": "PhysioNet / MIMIC-IV",
      "maintainer": "MIT Laboratory for Computational Physiology",
      "domain": "Clinical records",
      "summary": "De-identified electronic health records from real ICU and ED admissions at Beth Israel Deaconess — labs, vitals, medications, notes. The workhorse dataset of clinical machine-learning research.",
      "formats": "CSV; BigQuery",
      "size": "~tens of GBs",
      "license": "PhysioNet Credentialed Health Data License (free; DUA + CITI training required)",
      "updated": "Versioned releases",
      "access": "free, credentialed",
      "url": "https://physionet.org/content/mimiciv/",
      "download_url": ""
    },
    {
      "id": "chembl",
      "name": "ChEMBL",
      "maintainer": "EMBL — European Bioinformatics Institute",
      "domain": "Bioactivity & molecules",
      "summary": "A manually curated database of bioactive molecules with drug-like properties: 2.4M+ compounds, 20M+ activity measurements against biological targets, downloadable as a complete database.",
      "formats": "SQLite / PostgreSQL / MySQL dumps; SDF; web API",
      "size": "~GBs",
      "license": "CC BY-SA 3.0",
      "updated": "~2 releases/year",
      "access": "direct download",
      "url": "https://www.ebi.ac.uk/chembl/",
      "download_url": "https://ftp.ebi.ac.uk/pub/databases/chembl/ChEMBLdb/latest/"
    },
    {
      "id": "drugbank-open",
      "name": "DrugBank Open Data",
      "maintainer": "DrugBank (University of Alberta / OMx)",
      "domain": "Drugs & safety",
      "summary": "The freely licensed subset of DrugBank: the open drug & drug-target vocabulary (identifiers, names, CAS/UNII mappings) released under CC0. The full database requires a license — this subset does not.",
      "formats": "CSV (zipped)",
      "size": "~MBs",
      "license": "CC0 1.0 (open subset only)",
      "updated": "With DrugBank releases",
      "access": "free registration",
      "url": "https://go.drugbank.com/releases/latest#open-data",
      "download_url": ""
    },
    {
      "id": "rxnorm",
      "name": "RxNorm",
      "maintainer": "U.S. National Library of Medicine",
      "domain": "Drugs & safety",
      "summary": "The normalized naming system that lets U.S. drug databases talk to each other — every clinical drug, dose form, and brand mapped to stable identifiers. Full monthly releases downloadable with a free UMLS account.",
      "formats": "RRF (pipe-delimited); API (JSON)",
      "size": "~100s of MBs",
      "license": "Free; UMLS Metathesaurus License (free account) for full files",
      "updated": "Monthly",
      "access": "free registration",
      "url": "https://www.nlm.nih.gov/research/umls/rxnorm/",
      "download_url": ""
    }
  ]
}