An artificial intelligence model that evaluates heart signals recorded by smartwatches may help flag a hidden and dangerous heart condition called left ventricular systolic dysfunction (LVSD), according to preliminary, independent late-breaking science presented at the American Heart Association's Scientific Sessions 2026 in Chicago. The condition occurs when the heart's main pumping chamber, the left ventricle, does not contract effectively; in the study it was defined as a left ventricular ejection fraction of 40% or less. LVSD can be present without symptoms, and without treatment it can lead to symptomatic heart failure.
The research matters because it explores whether consumer devices already worn by millions could serve as an early warning system pointing people toward traditional screening exams such as an echocardiogram, an ultrasound scan of the heart. The study evaluated a novel AI model, developed by Medical AI Co., Ltd., that analyzed smartwatch ECG recordings for signs of reduced heart pumping function. "Some people have reduced heart pumping function without noticeable symptoms," said study author Hak Seung Lee, M.D., FAHA, chief medical officer of Medical AI Co., Ltd. and a cardiologist at the Digital Healthcare Institute, Sejong Medical Research Institute in Incheon, South Korea. "Our study explored whether AI analysis of smartwatch ECGs could help identify people who may benefit from additional screening for LVSD or other heart conditions."
Among 2,211 adults scheduled for an echocardiogram at an outpatient cardiology clinic, ECGs were recorded on both an Apple Watch and a Samsung Galaxy Watch during the same visit. The AI model distinguished people with and without LVSD about equally well on both watches. However, when the same AI-score cutoff, set in advance using separate Galaxy Watch data, was applied to both groups, 200 participants (9%) were classified as positive on one watch and negative on the other.
A second group of 146 adults recorded ECGs at home via smartwatches. Among 108 participants who recorded on at least five days in the first week, requiring positive AI results on at least 2 of 3 consecutive recording days halved false-positive LVSD classifications, from 18 to 9 among the 70 participants who did not have LVSD. That rule identified 31 of 38 participants with LVSD, compared with 33 when single-positive days were analyzed, meaning two additional cases were missed. Among all 146 home-recording participants, 81% of those with consistently positive results had LVSD confirmed by echocardiography, versus about 6% of those with consistently negative results. Nearly half had mixed results, and 40% of that group had confirmed LVSD.
"A single smartwatch ECG is a snapshot, and repeated recordings can give different results," Lee said. "Requiring repeated positive results reduced false positives in our study, yet it also missed some additional cases that should have been positive. Larger studies are needed to determine how best to use these results to guide further evaluation."
The study has limitations: it was conducted at one hospital in South Korea among patients referred for echocardiography, so results may not apply to the general population, and the repeat-testing comparison included only 108 participants. It did not determine whether using these AI results leads to earlier treatment, fewer hospitalizations or improved survival. The findings are considered preliminary until published as a full manuscript in a peer-reviewed journal. The abstract is available in the meeting's Online Program Planner, and multimedia accompanies the release link. Background on the measurement is available in the Association's Ejection Fraction Heart Failure Measurement guidance, and the Association's overall financial information is available here. The original release can be viewed on www.newmediawire.com.
