AI Tool Uses Smartwatch ECG to Detect Structural Heart Disease

An artificial intelligence algorithm paired with single-lead electrocardiogram sensors on smartwatches can accurately diagnose structural heart diseases, according to preliminary research to be presented at the American Heart Association's Scientific Sessions 2025. The study represents the first prospective demonstration that AI can detect multiple structural heart conditions using measurements from the electrical heart sensors found on common wearable devices.

Researchers developed the AI tool using more than 266,000 12-lead ECG recordings from over 110,000 patients at Yale New Haven Hospital between 2015 and 2023. The algorithm was specifically designed to identify structural heart disease from single-lead ECGs that resemble those obtained from smartwatch sensors. To prepare the model for real-world conditions, researchers incorporated simulated interference or "noise" into the training data, making the AI more resilient when dealing with imperfect signals from consumer devices.

"Millions of people wear smartwatches, and they are currently mainly used to detect heart rhythm problems such as atrial fibrillation," said study author Arya Aminorroaya, M.D., M.P.H., an internal medicine resident at Yale New Haven Hospital. "Structural heart diseases, on the other hand, are usually found with an echocardiogram, an advanced ultrasound imaging test of the heart that requires special equipment and isn't widely available for routine screening."

The research team validated their algorithm using data from 44,591 adults at four community hospitals and 3,014 participants from the population-based ELSA-Brasil study. The Brazilian Longitudinal Study of Adult Health (ELSA-Brasil) gathers important information about how chronic diseases develop and progress, focusing mainly on cardiovascular diseases and diabetes. Additional information about the study is available at https://www.elsa.org.br.

In the prospective real-world evaluation, 600 participants underwent 30-second, single-lead ECGs using smartwatches on the same day they received heart ultrasound scans. The analysis revealed that the AI model maintained high performance at 88% for detecting structural heart disease using smartwatch data, compared to 92% accuracy when using single-lead ECGs obtained from hospital equipment. The algorithm demonstrated 86% sensitivity for identifying people with heart disease and achieved 99% negative predictive value for accurately ruling out heart conditions.

"On its own, a single-lead ECG is limited; it can't replace a 12-lead ECG test available in health care settings," said Rohan Khera, M.D., M.S., the study's senior author and director of the Cardiovascular Data Science Lab. "However, with AI, it becomes powerful enough to screen for important heart conditions. This could make early screening for structural heart disease possible on a large scale, using devices many people already own."

The study population had a median age of 62 years, with approximately half being women and diverse racial and ethnic representation. About 5% of participants were found to have structural heart disease on heart ultrasound. The AI tool successfully identified conditions including weakened pumping ability, damaged valves, and thickened heart muscle - conditions that often progress without symptoms until serious complications occur.

Study limitations include the small number of patients with confirmed disease in the prospective evaluation and the presence of false positive results. The research abstract is available through the American Heart Association's Scientific Sessions 2025 Online Program Planner at https://professional.heart.org. The findings are considered preliminary until published as a full manuscript in a peer-reviewed scientific journal.

Researchers plan to evaluate the AI tool in broader settings and explore integration into community-based heart disease screening programs. This approach could potentially transform preventive cardiovascular care by leveraging the widespread adoption of smartwatches for early detection of structural heart conditions that currently require specialized medical equipment and appointments.