AI medical trial: estimating ejection fraction (EF) from a wearable ECG with AI (Peerbridge, heart-failure screening)
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.
Trial overview (primary data)
- StatusRecruiting
- ConditionsVentricular Ejection Fraction, LVF, LV Dysfunction, Atrial Enlargement, Conduction Defect, Heart Failure, Valvular Heart Disease, Ischemic Heart Disease, Cardiotoxicity, Myocardial Infarction, Dilated Cardiomyopathy, HFrEF - Heart Failure With Reduced Ejection Fraction
- InterventionsDEVICE: 15-minutes of sitting during COR ECG Acquistion
- SponsorPeerbridge Health, Inc
- Target enrollment2,000 participants
- Period2024-11-21 〜 2027-11-15
Key points
- Estimates ejection fraction (EF) severity with AI from an FDA-cleared wearable ECG
- The AI is evaluated as a Software-as-a-Medical-Device (SaMD), benchmarked against echocardiography (TTE)
- Prospective, multicenter, cluster-randomized; target 2,000 participants
- Aims to broaden heart-failure screening via inexpensive, everyday ECG + AI
- Peerbridge Health, 2024–2027, recruiting
- Echocardiography needs specialist equipment and an operator; the wearable estimates from five minutes recorded during fifteen minutes seated at rest.
1What a wearable ECG can reveal
Peerbridge Health's trial (NCT06699056) validates the accuracy of medical AI software that estimates the heart's pumping metric, ejection fraction (EF), from a wearable ECG.
2A cluster-randomized design
Per the registry summary, this is a prospective, multicenter, cluster-randomized controlled study of an investigational AI Software-as-a-Medical-Device (SaMD). The AI analyzes continuous ECG waveform data from the FDA-cleared "Peerbridge COR ECG Wearable Monitor" (an ambulatory patch worn during daily activities) to compute EF severity on the American Society of Echocardiography's 4-category scale.
EF severity is determined from a 5-minute ECG recording taken during a 15-minute seated rest, and compared against EF severity from an FDA-cleared non-contrast transthoracic echocardiogram (TTE) predicate. Target enrollment is 2,000; November 2024 – November 2027; recruiting.
3Ejection fraction as the measure
EF indicates how well the heart pumps blood and is used to diagnose and classify heart failure. It is usually assessed via echocardiography or cardiac MRI, which require specialized equipment and operators. Estimating severity from an inexpensive, everyday wearable ECG plus AI could broaden early detection and screening for heart failure.
4The reference test, and the test attempting to replace it
The trial verifies the accuracy of an AI estimate against an existing gold standard. Both measure the same thing while requiring quite different conditions.
Ejection fraction indicates how well the heart pumps blood and is used in diagnosing and classifying heart failure. This is a prospective, multicentre, cluster-randomised controlled trial targeting 2,000 cases from November 2024 to November 2027, recruiting. The AI is evaluated as software as a medical device.
Why it matters
Wearable-plus-AI cardiac screening is a widely watched area. Validating AI as a medical device (SaMD) against an established gold standard (echocardiography) is a useful example for the regulation and deployment of medical AI.
FAQ
What is ejection fraction (EF)?
What is SaMD?
Sources (primary)
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.
- ClinicalTrials.gov (study record, original)
- NCT ID: NCT06699056