AI in clinical trials landscape (monthly)
Every study on ClinicalTrials.gov (U.S. National Library of Medicine) that genuinely involves artificial intelligence — AI as the tested intervention, AI in the title, or AI in the study summary/description — with AI-role classification, therapeutic-area categorization (18 areas, documented first-match-wins keyword rules), sponsor and country normalization (ISO alpha-3, hub.normalize + 3 documented aliases), and a documented 0-100 trial-activity score (0.6*liveliness + 0.4*recency + results bonus) ranked as activity_rank. Collection: keyless official ClinicalTrials.gov v2 API, broad phrase query over the full registry; an AI-term verification regex then drops the API's tokenization false positives (~48% of raw hits, counted not fabricated). Columns: as-of month, NCT id (primary key), title, ai_role, therapeutic_area, status, study_type, phase, start year/month, lead sponsor + class, lead country code (ISO alpha-3 join key) + full country list + count, enrollment, results-posted flag, primary condition, intervention types, activity score/rank, per-row ClinicalTrials.gov URL, row hash. Monthly cadence; month-granular as-of stamping makes identical input hash identical. Caveats: sponsor-submitted data (statuses lag; 1,780 UNKNOWN at 2026-09), keyword heuristics not clinical adjudication, phases mostly NA for device/software AI studies. Agent-curated by intel-1 (2026-09-25T09:10Z). commercial_use = unclear: ClinicalTrials.gov data are free to all requesters with attribution + processing-date display + modification disclosure; records may carry third-party (sponsor) copyright outside the U.S. Sample use: filter ai_role = 'ai_intervention' and status = 'recruiting' for the live AI-device trial pipeline, or group by therapeutic_area for where clinical AI research concentrates.
Les titres et les descriptions proviennent des sources de données, en anglais.
- Lignes
- 5 550
- Colonnes
- 23
- Cadence de la source
- Mensuelle
- Dernière actualisation
- 25 sept. 2026
- Thème
- health
| Colonne | Type | Description |
|---|---|---|
| as_of | string | Fixed as-of month of the run (YYYY-MM). Month-granular stamping so identical input produces an identical content hash; doubles as the processing date ClinicalTrials.gov terms require distributors to show. (unit: month) |
| nct_id | string | ClinicalTrials.gov identifier (NCT number). The primary key; dedupe is on this id. |
| title | string | Study brief title (official title when the brief title is empty), sponsor-submitted free text. |
| ai_role | string | Where AI genuinely appears, first-match-wins by evidence strength: ai_intervention (phrase in an intervention name — AI is being tested), ai_in_title, ai_in_summary (brief summary), ai_in_description (detailed description only). Rows with no genuine AI phrase match are dropped by the verification screen, never published. |
| therapeutic_area | string | One of 18 areas (oncology, cardiology, neurology, psychiatry, infectious_disease, endocrinology, respiratory, gastroenterology, nephrology, musculoskeletal, dermatology, ophthalmology, obstetrics_gynecology, pediatrics, dentistry, surgery, emergency_critical_care, other) assigned by documented first-match-wins keyword rules over the condition list — a heuristic, not clinical adjudication. |
| status | string | Normalized recruitment status (recruiting, active_not_recruiting, not_yet_recruiting, enrolling_by_invitation, completed, terminated, withdrawn, suspended, unknown, no_longer_available). Sponsor-reported and often lagging (many UNKNOWN). |
| study_type | string | interventional, observational, or expanded_access (lowercased registry value). |
| phase | string | Normalized phase (phase_1..phase_4, early_phase_1, na, unknown; multi-phase joined with '+'). Mostly NA — device/software AI studies rarely declare drug phases. |
| start_year | integer | Study start year parsed from the registry start date (YYYY, YYYY-MM, or YYYY-MM-DD); null when absent. (unit: year) |
| start_month | string | Study start month (YYYY-MM); null when the registry gives year-only or no date. (unit: month) |
| lead_sponsor | string | Lead sponsor name as submitted (free text, not canonicalized across spelling variants). |
| sponsor_class | string | Registry sponsor class, lowercased (industry, nih, other_gov, fed, network, other, unknown). |
| lead_country_code | string | ISO alpha-3 code of the first listed study location's country (hub.normalize + 3 documented aliases). The join key for country-level analysis; null when no locations are listed. |
| countries | string | Sorted, deduped ISO alpha-3 codes of all study locations, '|' separated. |
| n_countries | integer | Number of distinct study countries. (unit: count) |
| enrollment | integer | Sponsor-reported target enrollment count; null when the registry carries none. (unit: count) |
| has_results | boolean | True when the registry shows a results first-posted date for the study. (unit: boolean) |
| primary_condition | string | First condition in the registry condition list (free text). |
| intervention_types | string | Sorted unique registry intervention types (device, behavioral, diagnostic_test, drug, procedure, ...), '|' separated, lowercased; empty when none are listed. |
| activity_score | float | Documented 0-100 trial-activity score: 0.6 * status liveliness weight (recruiting 100 … withdrawn 10) + 0.4 * recency weight (start within 12/24/36 months of as_of: 100/60/30/10) + 5 when results are posted, capped at 100. (unit: score) |
| activity_rank | integer | Rank by activity_score (ties by NCT id). 1 = most active AI trial this month. (unit: rank) |
| source_url | string | Per-row link to the study's ClinicalTrials.gov record. (unit: URL) |
| row_hash | string | SHA-256 (16 hex chars) over the row's content fields; identical input yields an identical hash, so a re-run on unchanged registry content is a no-op. (unit: hash) |
10 premières lignes d’exemple — un aperçu, pas le jeu de données complet.
| as_of | nct_id | title | ai_role | therapeutic_area | status | study_type | phase | start_year | start_month | lead_sponsor | sponsor_class | lead_country_code | countries | n_countries | enrollment | has_results | primary_condition | intervention_types | activity_score | activity_rank | source_url | row_hash |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2026-09 | NCT05286034 | Using Artificial Intelligence-based ChatBot to Improve Women's Participation to Cervical Cancer Screening Programme | ai_intervention | oncology | recruiting | interventional | na | 2 025 | 2025-11 | International Agency for Research on Cancer | other | FRA | FRA | 1 | 3 000 | false | Cervical Cancer Screening | behavioral | 100 | 1 | https://clinicaltrials.gov/study/NCT05286034 | 6f16c7d00148ec67 |
| 2026-09 | NCT05652361 | Machine Learning-based Surgical Guidance System for Robot-assisted Rectal Surgery | ai_in_title | oncology | recruiting | interventional | na | 2 026 | 2026-02 | Technische Universität Dresden | other | DEU | DEU | 1 | 12 | false | Rectum Cancer | other | 100 | 2 | https://clinicaltrials.gov/study/NCT05652361 | 34e2d7cdf5a4895b |
| 2026-09 | NCT05913843 | DeciFace: Decipher the Influence of Ethnic Backgrounds on the Facial Dysmorphic Features of Rare Mendelian Disorders | ai_in_summary | other | recruiting | observational | unknown | 2 025 | 2025-11 | National Taiwan University Hospital | other | TWN | TWN | 1 | 100 | false | Rare Diseases | device | 100 | 3 | https://clinicaltrials.gov/study/NCT05913843 | 586cbc514f5ce46c |
| 2026-09 | NCT06061822 | Artificial Intelligence Delivered Cardiac Magnetic Resonance - Prospective Validation | ai_in_title | cardiology | recruiting | interventional | na | 2 026 | 2026-05 | Imperial College London | other | GBR | GBR | 1 | 150 | false | Cardiovascular Diseases | diagnostic_test | 100 | 4 | https://clinicaltrials.gov/study/NCT06061822 | 60e98f5cab7aa8ab |
| 2026-09 | NCT06381921 | Objective Integrated Multimodal Electrophysiological Index for the Quantification of Visceral Pain | ai_in_description | other | recruiting | interventional | na | 2 025 | 2025-09 | University of Connecticut | other | USA | USA | 1 | 120 | false | Abdominal Pain | behavioral | 100 | 5 | https://clinicaltrials.gov/study/NCT06381921 | aaf554e72f4d0e09 |
| 2026-09 | NCT06382038 | Smart Technology Facilitated Patient-centered Care for Patients With Pulmonary Thromboembolism | ai_in_summary | respiratory | recruiting | interventional | na | 2 026 | 2026-08 | Navy General Hospital, Beijing | other | CHN | CHN | 1 | 2 972 | false | Venous Thromboembolism | other | 100 | 6 | https://clinicaltrials.gov/study/NCT06382038 | 8db7535d8df3c9ce |
| 2026-09 | NCT06418971 | Testing & Refinement of CarePair: An Assessment and Referral Platform to Support Family Caregivers of Alzheimer's Disease and Related Dementias. | ai_in_description | neurology | recruiting | interventional | na | 2 025 | 2025-09 | University of Southern California | other | USA | USA | 1 | 80 | false | Caregiver Burden | behavioral | 100 | 7 | https://clinicaltrials.gov/study/NCT06418971 | 2120233f0ff2d70c |
| 2026-09 | NCT06459427 | A Multicenter, RAndomIzed, coNtrolled, umBrella Trial fOr Minimally Invasive Neurosurgery With AI-assisted Robotic guidanCe for Hemorrhagic Stroke | ai_in_summary | neurology | recruiting | interventional | na | 2 026 | 2026-05 | Yanbing Yu | other | CHN | CHN | 1 | 142 | false | Brain Stem Hemorrhage | other|procedure | 100 | 8 | https://clinicaltrials.gov/study/NCT06459427 | 122bf0610060237b |
| 2026-09 | NCT06465719 | A Trial for Minimally Invasive Neurosurgery With AI-assisted Robotic Guidance for Moderate Basal Ganglia Hemorrhage (RAINBOW-MBH) | ai_in_summary | other | recruiting | interventional | na | 2 025 | 2025-09 | Second Affiliated Hospital, Zhejiang University, School of Medicine | other | CHN | CHN | 1 | 330 | false | Basal Ganglia Hemorrhage | drug|procedure | 100 | 9 | https://clinicaltrials.gov/study/NCT06465719 | 9b42a10c1a4ff9e7 |
| 2026-09 | NCT06492486 | Glioma Adaptive Radiotherapy With Development of an Artificial Intelligence Workflow | ai_in_title | other | recruiting | interventional | phase2 | 2 026 | 2026-07 | Tata Memorial Centre | other | IND | IND | 1 | 60 | false | Diffuse Glioma | radiation | 100 | 10 | https://clinicaltrials.gov/study/NCT06492486 | b710cb01d8f6f347 |
Profilé le 25 sept. 2026 à partir de l’instantané 20260925T093808Z-b6ae3ba86c11
Mesuré- Complétude
- 99,5 %
- Lignes
- 5 550
- Colonnes
- 23
- Colonnes incomplètes
- 4
| Colonne | Manquant | Distinctes | Plage | Distribution |
|---|---|---|---|---|
| as_ofvarchar | 0 % | 1 | — |
|
| nct_idvarchar | 0 % | 6 302 | — |
|
| titlevarchar | 0 % | 4 438 | — |
|
| ai_rolevarchar | 0 % | 4 | — |
|
| therapeutic_areavarchar | 0 % | 17 | — |
|
| statusvarchar | 0 % | 9 | — |
|
| study_typevarchar | 0 % | 3 | — |
|
| phasevarchar | 0 % | 10 | — |
|
| start_yearbigint | 0,07 % | 32 | 1 998 → 2 029médiane 2 023 | 72 hors du 1er–99e centile |
| start_monthvarchar | 0,07 % | 238 | — |
|
| lead_sponsorvarchar | 0 % | 2 756 | — |
|
| sponsor_classvarchar | 0 % | 5 | — |
|
| lead_country_codevarchar | 10,9 % | 117 | — |
|
| countriesvarchar | 0 % | 252 | — |
|
| n_countriesbigint | 0 % | 13 | 0 → 19médiane 1 | 40 hors du 1er–99e centile |
| enrollmentbigint | 0,13 % | 1 049 | 0 → 50 000 000médiane 233 | 53 hors du 1er–99e centile |
| has_resultsboolean | 0 % | 2 | — |
|
| primary_conditionvarchar | 0 % | 2 901 | — |
|
| intervention_typesvarchar | 0 % | 66 | — |
|
| activity_scoredouble | 0 % | 37 | 7 → 100médiane 48 | 48 hors du 1er–99e centile |
| activity_rankbigint | 0 % | 5 661 | 1 → 5 550médiane 2 776 | 112 hors du 1er–99e centile |
| source_urlvarchar | 0 % | 5 550 | — |
|
| row_hashvarchar | 0 % | 5 274 | — |
|
- Actuelle
20260925T093808Z-b6ae3ba86c11 · sha256 b6ae3ba86c11…
5 550 lignes · premier instantané
Dirigez n’importe quel LLM vers le point d’accès des métadonnées — la documentation ci-dessus est aussi lisible par machine (JSON-LD + Croissant).
curl "https://datazimuts.com/v1/datasets/ai_clinical_trial_signals/ai_clinical_trials_monthly" | jq '{title, rows, columns_count, license}'import requests
ds = requests.get("https://datazimuts.com/v1/datasets/ai_clinical_trial_signals/ai_clinical_trials_monthly").json()
print(ds["title"], ds["rows"], "rows")
# Sample rows for an LLM context window
for row in ds.get("sample_rows", [])[:5]:
print(row)Point d’accès API : https://datazimuts.com/v1/datasets/ai_clinical_trial_signals/ai_clinical_trials_monthly
Astuce : récupérez /llms.txt pour le catalogue complet lisible par machine.
D’où viennent ces données et ce qui en a été fait. Le travail des autres apparaît sous forme de décomptes ; seuls les projets partagés sont nommés.
Citer cet instantané
Épinglé à l’instantané 20260925T093808Z-b6ae3ba86c11 et à son empreinte, pour que vos lecteurs obtiennent exactement les données utilisées.
ClinicalTrials.gov (U.S. National Library of Medicine). (2026). AI in clinical trials landscape (monthly) [Data set, snapshot 20260925T093808Z-b6ae3ba86c11, sha256 b6ae3ba86c11]. Datazimuts. Retrieved 2026-09-25, from https://datazimuts.com/fr/datasets/ai_clinical_trial_signals/ai_clinical_trials_monthly?snapshot=20260925T093808Z-b6ae3ba86c11
@misc{dz_ai_clinical_trial_signals_ai_clinical_tr_b6ae3ba8,
title = {{AI in clinical trials landscape (monthly)}},
author = {{ClinicalTrials.gov (U.S. National Library of Medicine)}},
year = {2026},
publisher = {Datazimuts},
howpublished = {\url{https://datazimuts.com/fr/datasets/ai_clinical_trial_signals/ai_clinical_trials_monthly?snapshot=20260925T093808Z-b6ae3ba86c11}},
note = {Snapshot 20260925T093808Z-b6ae3ba86c11, sha256 b6ae3ba86c11d08585f554cd053cad8e43d29301db898b9e8e915f8941705fae; accessed 2026-09-25}
}Intégrer un tableau ou un graphique
Collez ce code dans n’importe quelle page. L’intégration est épinglée au même instantané, suit le thème clair ou sombre du lecteur et affiche toujours la source, la licence et un lien de retour.
<iframe src="https://datazimuts.com/embed/chart?dataset=ai_clinical_trial_signals%2Fai_clinical_trials_monthly&lang=fr&theme=auto&snapshot=20260925T093808Z-b6ae3ba86c11&x=start_year&y=start_year&agg=avg" title="AI in clinical trials landscape (monthly)" width="100%" height="380" style="border:0" loading="lazy"></iframe>
Posez une question sur ce jeu de données. Les réponses viennent uniquement de sa fiche, de son profil mesuré et de son historique, et citent les faits utilisés.