An artificial intelligence (AI) algorithm combined with the single-lead electrocardiogram (ECG) sensor on a smartwatch accurately identified structural heart diseases, such as weakened pumping ability, damaged valves, or thickened heart muscle, according to a preliminary study presented at the American Heart Association's Scientific Sessions 2025. The research, conducted by scientists at Yale School of Medicine and other institutions, marks the first prospective study to demonstrate that an AI tool can detect multiple structural heart conditions using only a smartwatch's ECG sensor.
"Millions of people wear smartwatches, and they are currently mainly used to detect heart rhythm problems such as atrial fibrillation. 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," said study author Arya Aminorroaya, M.D., M.P.H., an internal medicine resident at Yale New Haven Hospital and a research affiliate at the Cardiovascular Data Science (CarDS) Lab at Yale School of Medicine. "In our study, we explored whether the same smartwatches people wear every day could also help find these hidden structural heart diseases earlier, before they progress to serious complications or cardiac events."
The researchers developed the AI algorithm using over 266,000 12-lead ECG recordings from more than 110,000 adults. They then adapted the algorithm to interpret single-lead ECGs, simulating the data from smartwatches by isolating one lead and adding noise to mimic real-world conditions. The model was externally validated using data from community hospitals and the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Finally, they prospectively recruited 600 participants who underwent 30-second single-lead ECGs using a smartwatch on the same day they received a heart ultrasound.
The analysis found that the AI model performed with high accuracy: it achieved 92% on a standard performance scale when using single-lead ECGs from hospital equipment, and 88% when using smartwatch-recorded ECGs. The algorithm correctly identified 86% of individuals with structural heart disease and had a 99% negative predictive value, meaning it was highly reliable in ruling out disease.
Study senior author Rohan Khera, M.D., M.S., director of the CarDS Lab, noted, "On its own, a single-lead ECG is limited; it can't replace a 12-lead ECG test available in health care settings. 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's limitations include a small number of patients with the disease in the prospective cohort and a number of false positive results. The researchers plan further evaluation in broader settings and exploration of integration into community-based screening programs. The findings are considered preliminary until published in a peer-reviewed journal.
For more details, the abstract is available at the American Heart Association's Scientific Sessions 2025 Online Program Planner. Additional resources can be found on the American Heart Association newsroom.
