AI Tool Detects Structural Heart Disease Using Smartwatch ECG Sensors
An artificial intelligence algorithm paired with smartwatch ECG sensors can accurately detect structural heart diseases, potentially making early screening more accessible to millions of people who already own these devices.
An artificial intelligence algorithm paired with the single-lead electrocardiogram sensors on smartwatches accurately diagnosed structural heart diseases, according to a preliminary study to be presented at the American Heart Association's Scientific Sessions 2025. The research represents the first prospective study showing that AI can detect multiple structural heart diseases using measurements from the single-lead ECG sensor found on the back and digital crown of consumer smartwatches.
Millions of people wear smartwatches that are currently mainly used to detect heart rhythm problems such as atrial fibrillation. Structural heart diseases, including weakened pumping ability, damaged valves or thickened heart muscle, are typically identified through echocardiograms - advanced ultrasound imaging tests requiring specialized equipment not widely available for routine screening. The study explored whether everyday smartwatches could help detect these hidden structural conditions earlier, before they progress to serious complications or cardiac events.
Researchers developed the AI algorithm using more than 266,000 12-lead ECG recordings from over 110,000 adults at Yale New Haven Hospital between 2015 and 2023. They created an algorithm to identify structural heart disease from single-lead ECGs similar to those obtained from smartwatch sensors. The team accounted for random interference or noise that could arise during real-world smartwatch recordings, making the AI more resilient when dealing with imperfect signals. The model was externally validated using data from community hospitals and the population-based ELSA-Brasil study, which gathers information about chronic disease development with focus on cardiovascular conditions and diabetes.
In the prospective real-world study, 600 participants underwent 30-second single-lead ECGs using smartwatches on the same day they received heart ultrasounds. The analysis revealed the AI model scored 92% on standard performance metrics when using single-lead ECGs from hospital equipment, and maintained 88% performance when detecting structural heart disease from smartwatch-obtained ECGs. The algorithm accurately identified most people with heart disease with 86% sensitivity and demonstrated 99% accuracy in ruling out heart disease.
Study author Arya Aminorroaya, M.D., M.P.H., an internal medicine resident at Yale New Haven Hospital, emphasized the accessibility implications of this technology. Rohan Khera, M.D., M.S., the senior author and director of the Cardiovascular Data Science Lab at Yale, noted that while a single-lead ECG alone is limited and cannot replace 12-lead ECG tests available in healthcare settings, when combined with AI it becomes powerful enough to screen for important heart conditions. This could enable early screening for structural heart disease on a large scale using devices many people already own.
The study limitations include a small number of patients with actual disease in the prospective study and some false positive results. Researchers plan to evaluate the AI tool in broader settings and explore integration into community-based heart disease screening programs to assess potential impact on improving preventive care. The findings are considered preliminary until published as full manuscripts in peer-reviewed scientific journals, as abstracts presented at American Heart Association scientific meetings are not peer-reviewed. Additional information about the study is available in the abstract and through the American Heart Association's Scientific Sessions 2025 Online Program Planner at https://professional.heart.org/en/meetings/scientific-sessions.