Research Intelligence Methodology

NCBI E-utilities API (ESearch → EFetch), daily incremental runs. Records deduplicated by PMID.

Publication dates from January 2000 forward. Incremental runs re-query with a moving minimum date so only new records are fetched.

A publication is included if it matches either landscape query (AI/ML terms co-occurring with health context terms) or is affiliated with a tracked health AI company. MeSH terms assigned by the National Library of Medicine are stored with every record and drive clinical-area categorization downstream.

api.biorxiv.org, both servers (bioRxiv and medRxiv), daily. The API has no server-side search, so all filtering happens at insert time. Deduplicated by DOI.

All patterns use word boundaries and case-insensitive matching to avoid false positives (e.g., "LLM" must be a standalone token).

A preprint is stored only if it matches at least one pattern. The specific matched keywords are saved on every record for auditability, so any inclusion can be traced back to the exact terms that triggered it.

NIH RePORTER Projects API v2 (POST /v2/projects/search), paginated per fiscal year to stay under the API result cap. Deduplicated by application ID.

Fiscal years 2000–2026 for the full backfill; nightly incremental runs cover the current and prior fiscal year. A separate organization pass queries org_names for every tracked company.

A grant is included if any landscape term matches its title or NIH-indexed terms, or if its recipient organization is a tracked health AI company. Project abstracts, funding amounts, PI details, and administering institute are stored in full.

OpenAlex API (free, keyless, polite pool via contact email), nightly incremental. Publications matched by PMID in batches.

Chosen over Google Scholar, which has no API and blocks automation. cited_by_count is refreshed for new publications each night; existing counts are backfilled periodically.

ClinicalTrials.gov API v2, daily incremental. Deduplicated by NCT ID; updated trials are refreshed in place.

The landscape query searches all indexed trial text (interventions, conditions, titles, summaries). Incremental runs fetch only trials whose registry record changed since the last run.

A trial is included if it matches the AI/ML landscape query or names a tracked company. Phase, enrollment, status, sponsor class, design fields (allocation, masking, age groups), and MeSH condition/intervention terms are stored in full.

Status fields come directly from the registry record. Stop-reason classification runs nightly on new stopped trials.

Many AI trials are observational or device-based and do not use traditional drug phases (marked N/A). The ~21,500 stopped trials carrying a free-text stop reason are classified by an LLM into seven buckets — enrollment, funding, business decision, safety/efficacy, COVID-19, data/results, other — which powers the "Why Trials Stop" analysis on Clinical Validation pages. Classifications are stored per trial and never overwrite registry data.

The official FDA AI-Enabled Medical Device List CSV is downloaded from fda.gov and upserted daily. Each device is then enriched via exact submission-number lookups on openFDA (device/510k by K-number, device/pma, device/classification).

The FDA list itself is the inclusion criterion — we do not decide what counts as an "AI-enabled device"; the FDA does. Clinical areas are assigned in two passes: the FDA review panel deterministically sets the primary area, then an LLM reads the device description and intended use to add one to three secondary areas the panel label alone would miss.

openFDA device/recall + device/enforcement (recalls) and device/event (MAUDE adverse event reports), daily incremental with a 14-day lookback window to catch late-arriving records.

Recalls and adverse events are linked to AI devices by FDA product code — the same code family the device was cleared under. Both AI-linked and broader device-safety records are retained so AI device safety can be benchmarked against the wider device landscape.

Hand-curated registry maintained in code with every entry source-verified against primary CMS and AMA documents.

Inclusion requires verification against primary sources (CMS Medicare Physician Fee Schedule, CMS billing articles, AMA CPT releases); draft or rumored codes are excluded. Each entry carries the code, official descriptor, code type (Category I / Category III / HCPCS), AMA Appendix S taxonomy tier (assistive / augmentative / autonomous), clinical area, example devices, effective date, status, and source notes. A small number of non-AI "context codes" (e.g., the 92227–92229 retinal imaging family) are retained and flagged for trend comparison.

data.cms.gov "Medicare Physician & Other Practitioners — by Provider and Service" datasets, one fixed dataset per calendar year (2013–2024), refreshed when CMS publishes a new annual release.

Only rows whose HCPCS code appears in our curated AI reimbursement code registry are ingested — utilization is measured strictly for verified AI codes.

Service counts, provider counts, and average payment amounts are aggregated per code per year. Because CMS data lags roughly two years, the most recent year shown is the latest CMS release, not the current calendar year.

USAspending API v2 (spending_by_award), contract award types A–D, award period 2016 to present, paginated and deduplicated by award ID.

Keyword search casts a wide net by design; a second-stage LLM relevance screen then evaluates every contract description individually.

A contract is kept only if it is genuinely about AI/ML applied to healthcare, medicine, clinical care, biomedical research, or health administration. Explicitly rejected: generic IT infrastructure, non-health AI, staffing contracts without AI substance, and non-AI health services. Roughly 21% of fetched contracts pass (346 of 1,650 at last count); passing contracts are tagged to one to three clinical areas with confidence scores, and rejected ones are retained but excluded from dashboards.

SEC XBRL companyconcept API, queried per company CIK with quarterly refresh cadence.

Only companies in our tracked public-company list are pulled. Values come directly from company XBRL filings with no restatement or adjustment on our side.