ClinicalTrials.gov

Tracking AI in medicine — clinical trials

From the U.S. NIH clinical-trial registry ClinicalTrials.gov, clinical trials of AI (artificial intelligence / machine learning) in medicine and diagnostics, organized with conditions, sponsor, and status. This site is not an official U.S. government website.

This page organizes public data and is not medical advice or diagnosis. Decisions such as trial participation should be based on your physician and official information. We do not handle individual patient data.

Browse all collected data (list, filter, search) →

Featured

Notable AI medical trials explained with key points, FAQs, and sources.

Recruiting Antenatal Care / Maternal Health

Medical-AI trial: AI-assisted "blind-sweep" obstetric ultrasound by non-specialists — antenatal screening in rural DR Congo (SPAQ E-con AI) (NCT07677670)

SOIK Corporation Sarl

A multicenter prospective study evaluating the diagnostic accuracy and implementation feasibility of an AI-assisted blind-sweep obstetric ultrasound (SPAQ E-con AI), operated by trained non-specialist health workers, for antenatal screening in rural Democratic Republic of the Congo. Primary outcomes are gestational-age mean absolute error (trimesters 2 and 3) and AI confidence calibration. Target ~1,430 (IRB ceiling 3,000). Recruiting.

Recruiting Bladder Cancer / Non-muscle Invasive Bladder Cancer

Before AI reaches blue-light cystoscopy for bladder cancer — an observational study that registers the collection of training data itself (NCT07144319)

Photocure

An observational study that gathers video and image recordings together with clinical data from blue light cystoscopy (BLC) performed in routine care, in order to build a training dataset for a real-time lesion detection (CADe) algorithm. Planned enrollment 500; the sponsor is a company (Photocure).

Recruiting Genetic Conditions

AI medical trial: a natural-history study collecting medical data on genetic conditions to build "advanced data analytics" (AI) tools (NHGRI observational study) — a clinical trial (ClinicalTrials.gov)

National Human Genome Research Institute (NHGRI)

A natural-history (observational) study collecting medical and genetic data from people with (or suspected to have) genetic conditions, and their relatives. The data aims to help develop advanced data-analytics tools for better analyzing and understanding genetic data.

Recruiting Type 2 Diabetes / Diabetes Mellitus Type 2

An AI-designed microbiome-targeted supplement tested for glycemic control in type 2 diabetes — with the record stating expressly that no AI runs during the trial (ENBIOSIS, NCT07622628)

ENBIOSIS BIOTECHNOLOGIES

A randomized study of whether a microbiome-targeted nutritional product improves blood sugar control in adults with type 2 diabetes when added to usual stable treatment, compared with placebo over 24 weeks. The product was designed using AI before the study began, but a single fixed formulation is used for everyone in the active group and AI performs no personalization during the trial.

Recruiting High-risk Cardiac Patients

Medical-AI trial: real-world registry of the Willem AI-based ECG platform (high-risk cardiac patients, large-scale observational) (NCT07333547)

Idoven 1903 S.L.

A large-scale registry study collecting real-world performance of Willem (Idoven), a platform that interprets ECGs automatically with AI. It evaluates the performance of Willem in detecting cardiac abnormalities on the ECGs of high-risk cardiac patients admitted to cardiovascular units. Single-group observational; retrospective + prospective; target 200,000; recruiting.

Active, not recruiting Primary Open-Angle Glaucoma (POAG) / Ocular Hypertension

Comparing preservative-free and preserved glaucoma eye drops, with chatbot follow-up — one of only 35 trials in 803 that carry a phase (Tecnoquimicas, NCT07690397)

Tecnoquimicas

A Phase 4 trial in patients with primary open-angle glaucoma or ocular hypertension comparing a preservative-free dorzolamide-timolol-brimonidine combination against one containing preservatives. The primary aim is ocular surface safety, with adherence, therapeutic efficacy and biomolecular markers also compared. Chatbot follow-up appears in the title.

Recruiting Hypertension, Pulmonary / Heart Failure With Reduced Ejection Fraction

Detecting pulmonary hypertension and low ejection fraction from a digital stethoscope and three-lead ECG — catching conditions that rarely announce themselves (Eko Devices, NCT07087613)

Eko Devices, Inc.

A prospective observational study of whether heart sounds and three-lead electrocardiograms recorded with a digital stethoscope can help detect pulmonary hypertension and a left ventricular ejection fraction of 40 percent or less. Echocardiography or right heart catheterization serves as the reference standard, with up to 3,850 participants planned.

Active, not recruiting Osteo Arthritis Knee / Knee Arthritis

A knee replacement with built-in sensors recording gait after surgery — implants appear in 11 of the 803 trials this site holds as of 2026-08-31 (Zimmer Biomet, NCT06089291)

Zimmer Biomet

A prospective multicenter longitudinal cohort study of Persona IQ, a knee replacement with built-in sensors. Kinematic gait metrics captured through remote therapeutic monitoring are used to develop correlative measures helping surgeons understand and manage recovery. Planned enrollment is 200.

Recruiting Graves Disease / Hyperthyroidism/Thyrotoxicosis

AI medical trial: detecting thyrotoxicosis from consumer-wearable heart rate with AI (Thyroscope, Glandy HYPER)

THYROSCOPE INC.

An observational study evaluating whether the AI software device "Glandy HYPER" can detect a thyrotoxic state in hyperthyroidism (Graves' disease) using heart-rate data from commercial wearables, correlated with thyroid function tests (free T4).

Recruiting Ventricular Ejection Fraction / LVF

AI medical trial: estimating ejection fraction (EF) from a wearable ECG with AI (Peerbridge, heart-failure screening)

Peerbridge Health, Inc

A multicenter trial by Peerbridge Health validating an investigational AI Software-as-a-Medical-Device that estimates ejection fraction (EF) severity from continuous ECG captured by an FDA-cleared wearable patch, compared against echocardiography.

Completed Lung Cancer / Breast Cancer

AI medical trial: AstraZeneca evaluates "AI pathology" in real-world lung and breast cancer practice (multinational, observational)

AstraZeneca

A multinational observational study by AstraZeneca evaluating how computational pathology plus AI algorithms are used in the pathology workup of patients with suspected lung and breast cancer — gauging how far AI has entered routine pathology.

Completed High-Risk Multidisciplinary Care / Clinical Decision Support

Testing whether a structural verification layer on AI-assisted care reduces safety failures — two questions in one three-arm randomized trial (Waymark, NCT07597499)

Waymark

A three-arm 1:1:1 patient-level randomized trial in real high-risk multidisciplinary encounters testing whether adding a clinical AI structural verification layer to an AI-assisted physician workflow reduces clinically meaningful safety failures, and whether the AI-assisted workflow itself improves the same endpoint against unassisted standard care. It enrolled 240 patients across three states over 12 weeks.

Completed Pneumothorax / Pulmonary Nodule, Solitary

AI medical trial: "Carebot AI CXR" reads chest X-rays vs. radiologists (completed)

Carebot s.r.o.

A multi-reader retrospective study evaluating how accurately the AI chest X-ray tool "Carebot AI CXR" (a deep-learning automated detection system) detects findings such as pneumothorax, pulmonary nodules, atelectasis, cardiomegaly, and pleural effusion compared with individual radiologists. Completed with 956 cases.

Recruiting Colo-rectal Cancer

Randomizing patients, and changing the care itself — a nationwide trial that hands colorectal surgery risk assessment to AI — a clinical trial (ClinicalTrials.gov)

Zealand University Hospital

A researcher-initiated trial across Danish hospitals randomizing 1,200 patients scheduled for curative colorectal cancer surgery to risk assessment by a surgeon using standard methods or by a surgeon with AI assistance. Because the level of perioperative care follows from the assessed risk, the AI output reaches the care patients actually receive.

Recruiting Uterine Cancer / Rectal Cancer

Medical-AI trial: protecting the ovaries with AI adaptive radiotherapy (OvAR-Y) — pelvic cancer in young women and oncofertility (in-silico) (NCT06904365)

Washington University School of Medicine

An observational study using in-silico (computer simulation on real data) to test the feasibility of ovarian-sparing adaptive radiotherapy for women under 50 who need pelvic radiation for cancers such as uterine and rectal. It addresses the unmet need to reduce the risk of premature ovarian failure. 10 cases.

Recruiting Caries,Dental

Does AI caries detection work differently for novices and experts — a randomized trial measuring the effect on the treatment threshold — a clinical trial (ClinicalTrials.gov)

University of Michigan

A randomized trial asking whether the effect of AI on detecting caries in radiographs depends on the experience of the person reading them, comparing detection and subsequent treatment decisions between early and experienced learners.

Recruiting Cardiac Arrhythmias / Acute Myocardial Infarction (AMI)

AI aimed at false alarms and alarm fatigue on cardiac monitors — predicting critical arrhythmias in the coronary care unit — a clinical trial (ClinicalTrials.gov)

Catharina Ziekenhuis Eindhoven

An observational study applying AI to continuous ECG data from a coronary care unit to predict life-threatening arrhythmias 30 minutes and one day ahead. Reducing alarm fatigue through better detection is part of the aim.

Recruiting Adolescence Idiopathic Scoliosis

Machine learning to predict progression in adolescent idiopathic scoliosis — the aim is not diagnosis but optimizing how often X-rays are taken (NCT07556042)

Istanbul University

A study developing and validating a machine-learning model to predict the Cobb angle after a 12-week core stabilization exercise programme in adolescent idiopathic scoliosis (AIS). The aim is not diagnosis but reading progression well enough to optimize the frequency of follow-up radiography. Planned enrollment 30.

Active, not recruiting AI (Artificial Intelligence) / Large Language Model

The largest box is other — residents testing four language models against standard references

Cambridge Health Alliance

A study in which family medicine, internal medicine and psychiatry residents use OpenEvidence during actual practice, with their conclusions assessed for clinical appropriateness and compared against three other large language models. The registered intervention is other.

Recruiting Diffuse Glioma / Glioblastoma

Changing the dose mid-treatment — an AI workflow registered as radiation

Tata Memorial Centre

In radiotherapy for glioma, MRI and PET are performed twice during treatment and the dose altered according to what they show, with an AI workflow carrying out the alteration. The registered intervention is radiation.

Active, not recruiting Cancer / Intraoperative Pathology

Separating the building from the checking — an AI foundation model for intraoperative frozen-section pathology, validated internally, externally and prospectively — a clinical trial (ClinicalTrials.gov)

Sun Yat-Sen Memorial Hospital of Sun Yat-Sen University

A multicenter observational study putting frozen-section pathology tasks across multiple organ systems onto a single AI foundation model and testing how it performs. Retrospective development, internal validation and external validation are followed by prospective enrollment of patients actually undergoing intraoperative frozen section. Target enrollment is 33,000 and the primary outcome is the area under the ROC curve.

Active, not recruiting Difficult Intubation / Difficult Laryngoscopy

Showing general-purpose AI the same photographs the specialist sees — three models judged against anesthesiologists on predicting a difficult airway — a clinical trial (ClinicalTrials.gov)

Memorial Atasehir Hospital

A prospective observational study in adults scheduled for elective surgery requiring intubation. Standardized eight-view preoperative airway photographs are assessed by ChatGPT, Gemini and Grok under one structured prompt, and their predictions are compared with expert anesthesiologist assessments, conventional airway evaluation and what actually happened during surgery. Target enrollment is 319.

Recruiting Diagnostic Imaging / Eye Tracking

Medical-AI trial: when should AI advice appear? eye-tracking of visual search, diagnosis, and trust in chest X-ray reading (human-AI interaction) (NCT07675694)

University Hospitals, Leicester

A within-subject interventional study using eye-tracking to examine whether showing AI advice before or after a clinician first reviews a chest X-ray changes visual search, reading time, diagnostic decisions, confidence, and trust in AI. Healthcare professionals complete two reading sessions. 24 participants.

Recruiting Opioid Consumption, Postoperative

The AI decides who enters, not what is given — a trial registered as a drug

University of California, San Diego

A trial using a predictive model on electronic health record data to select surgical patients at high risk of persistent opioid use, then testing a non-opioid analgesic in them. What is registered as the intervention is the drug, not the AI.

Active, not recruiting Anemia (Diagnosis) / Anemia

Medical-AI trial: smartphone photo of the inner eyelid + AI to detect anemia non-invasively (NiADA / AnemiAI) vs. blood draw (3,000 participants) (NCT07678762)

Fabio Biscegli Jatene

A multicenter prospective study evaluating the diagnostic accuracy of NiADA, an app that photographs the lower eyelid conjunctiva with a smartphone and uses AI to estimate hemoglobin and detect anemia non-invasively, compared with the standard venous blood draw. Sensitivity and specificity are the primary endpoints. Target 3,000.

Recruiting Basal Cell Carcinoma

Medical-AI trial: predicting high/low risk and subtype of basal cell carcinoma from dermoscopy images with a CNN — compared with dermatologists (NCT07677124)

Istanbul Training and Research Hospital

A retrospective observational study evaluating whether a convolutional neural network (CNN) can classify basal cell carcinoma (BCC) as low- or high-risk and predict its histopathological subtype from clinical and dermoscopy images, and compares the model with dermatologists. Histopathology is the reference. Target 2,500; recruiting.

Recruiting Weaning From Mechanical Ventilation in Care Unit

Medical-AI trial: predicting the success of a spontaneous breathing trial with machine learning — ICU ventilator weaning from biosignals and biomarkers (NCT05886803)

Centre Hospitalier Universitaire de Nice

An observational study of whether machine learning can predict, from biosignals and biomarkers, the success of the spontaneous breathing trial (SBT) used to test weaning from a ventilator in the ICU. Weaning takes up much of an ICU stay, and the first attempt reportedly fails in about 20%. Target 500; recruiting.

Recruiting Coronary Artery Disease

Medical-AI trial: intravascular-ultrasound (IVUS)-based AI to improve outcomes after coronary stenting (INNOVATE-PCI) (NCT05807841)

Asan Medical Center

A prospective, multicenter observational study validating, in real practice, the diagnostic performance and clinical impact of machine-learning models based on coronary angiography and intravascular ultrasound (IVUS) during percutaneous coronary intervention (PCI, stenting). The primary outcomes are target-vessel failure (TVF) related to the treated (culprit) and untreated (nonculprit) lesions. 3,000 patients; recruiting.

Recruiting Periapical Diseases

Medical-AI trial: detecting periapical lesions from dental panoramic images with AI — catching easily missed root-tip lesions (CBCT reference) (NCT05888935)

Centre Hospitalier Régional Metz-Thionville

An observational study evaluating whether AI can detect periapical lesions (at the tip of a tooth root) from low-dose dental panoramic X-rays. Panoramic is a first-line examination, but detection rates for these lesions are low (20–36%), and cone-beam CT (CBCT) is used as the reference. The primary outcome is the performance of the AI software. 2,000 patients; recruiting.

Recruiting Gynecologic Cancer / Hereditary Cancer Syndrome

Medical-AI trial: a chatbot to bring hereditary-cancer genetic testing to an underserved population — reducing health inequity (NCT05562778)

Weill Medical College of Cornell University

An interventional study comparing a chatbot that uses AI and natural language processing against usual care, to see whether it can raise the rate of recommending genetic testing among patients at elevated risk of a familial cancer syndrome, in an all-Medicaid gynecology clinic. It also evaluates drivers of inequity in access to testing. The primary outcome is the proportion recommended for genetic testing. 150 patients; recruiting.

Latest (original, AI-in-medicine)

Recent clinical trials

Recently updated AI-in-medicine trials (original titles). Each links to the official ClinicalTrials.gov page.

Not yet recruiting Gemini Flash 3.6 Versus Human Observers for FIGO-Based Interpretation of Intrapartum... Assiut University ・ Fetal Hypoxia / Fetal Distress
Not yet recruiting Short- and Mid-term Therapeutic, Prognostic, and Societal Impact of Implementing Int... Fondation Hôpital Saint-Joseph ・ Lung Cancer (Non-Small Cell)
Not yet recruiting Designing a Large Language Model Architecture for Shared Decision Making and Informe... Harding Center for Risk Literacy ・ Shared Decision Making / Health Literacy
Recruiting AI-Personalized Discharge Education for Patients After Lung Cancer Surgery Xiamen University ・ Lung Cancer (Diagnosis)
Recruiting Artificial Intelligence Into Ultrasound Diagnostics in Reproductive Medicine Semmelweis University ・ Endometriosis / Adenomyosis of Uterus
Active, not recruiting Clinical Application of an AI-based Dissection Trajectory Prediction System (ADTPS)... Qilu Hospital of Shandong University ・ Esophageal Squamous Cell Carcinoma (ESCC) / High-Grade Intraepithelial Neoplasia
Enrolling by invitation Explainable AI for Predicting Hospital Admissions in Heart Failure: ExplAIn-HF Medisch Spectrum Twente ・ Heart Failure
Not yet recruiting Structured Nursing Intervention for Adults With Poorly Controlled Asthma: A Pilot St... Hospital San Carlos, Madrid ・ Asthma / Medication Adherence
Recruiting A Study to Compare Standard Therapy to Treat Hodgkin Lymphoma to the Use of Two Drug... National Cancer Institute (NCI) ・ Lugano Classification Limited Stage Hodgkin Lymphoma AJCC v8
Not yet recruiting Discovering Determinants of Food Intake by Application of Artificial Intelligence to... National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) ・ Healthy Volunteer
Completed Evaluation of Neoplasia With Artificial Intelligence in Gastrointestinal Endoscopy Portsmouth Hospitals NHS Trust ・ Gastrointestinal Neoplasms
Recruiting AI-Assisted Personalized Heat-Risk Alerts National University of Medical Sciences, Pakistan ・ Heat-related Illness / Chronic Disease
Recruiting Artificial Intelligence to Personalize Prostate Cancer Treatment (the HypoElect Tria... German Oncology Center, Cyprus ・ Prostate Cancer
Not yet recruiting Optimizing Chatbot Reminder Timing in a Chatbot Cessation Service: A Micro-Randomize... The University of Hong Kong ・ Smoking Cessation
Not yet recruiting Intraoperative Ultrasound for Brain Tumor Surgery Enhanced by AI Hospital del Rio Hortega ・ Brain Tumor Adult
Active, not recruiting Feasibility of Vision-Language Models for Detecting Physical Assistance as an Observ... Samsung Medical Center ・ Cerebral Palsy
Completed AI-Personalized Digital Exercise for University Students Transilvania University of Brasov ・ Physical Activity / Exercise Adherence
Not yet recruiting Diabetes Prevention AI: Enhancing Prevention Strategies Using Personalized Nutrition... Emory University ・ Pre Diabetes / Type2 Diabetes
Completed AI-Driven Consent Simplification Study University of California, Los Angeles ・ Informed Consent / Comprehension
Not yet recruiting AI-Stratified Myopia Control for Children in Remote Areas Shanghai Eye Disease Prevention and Treatment Center ・ Myopia
Completed AI-Generated Video Distraction Via Virtual Reality for Fear and Pain During Pediatri... Yuzuncu Yil University ・ Procedural Pain Relief / Virtual Reality
Not yet recruiting AI Assistance for Detecting Active Bleeding During DSA Procedures Zhongda Hospital ・ DSA / Bleeding
Not yet recruiting Development and Clinical Validation of a Smart Analysis System for a Wearable Cardia... Kunjing Pang ・ Cardiovascular Diseases
Recruiting Artificial Intelligence-supported Mobile Application for Patients With Breast Cancer Ege University ・ Breast Cancer / Chemotherapy Side Effects
Not yet recruiting External Validation of the FedHist Dynamic Early Warning Model for Mortality Risk in... Southeast University, China ・ ICU
Not yet recruiting Clinical and Cost-Effectiveness of an Artificial Intelligence -Synthesized Nursing C... Koç University ・ Medical Device Related Pressure Ulcer (MDRPU) / Pressure Injury
Recruiting Analyzing Retinal Microanatomy in Retinopathy of Prematurity to Improve Care Duke University ・ Retinopathy of Prematurity (ROP)
Not yet recruiting AI Chatbot for Prostate Radiation Therapy Patient Education Brigham and Women's Hospital ・ Prostate Cancer Patients
Not yet recruiting QAIAx (AIhealth4U) - AI Smart Health Cities: Microcity Enclave Program (Quantum AI/A... Veterans Recovery Network Inc. ・ Asperger's Disorder / Asperger Disorder
Not yet recruiting Multimodal Glucose Prediction in Type 2 Diabetes Johns Hopkins University ・ Type 2 Diabetes

Source: ClinicalTrials.gov (U.S. NIH/NLM, public domain). This site does not provide medical advice. Verify the latest and exact details with the official source. This site is not endorsed or certified by the NIH/NLM.