AI-powered stethoscope enhances early heart failure detection in primary care

A new study published in the Journal of the American College of Cardiology (JACC) Advances demonstrates that Eko Health’s artificial intelligence (AI)-powered digital stethoscope can effectively detect reduced ejection fraction (EF) — a key indicator of heart failure.

The findings suggest that this technology could enhance early diagnosis and intervention, especially in primary care settings where echocardiography is not always accessible.

The study, conducted across four U.S. health care networks, validated Eko Health’s AI model. Researchers enrolled 2,960 adults undergoing echocardiography and captured heart sound and electrocardiogram (ECG) data — using an ECG-enabled digital stethoscope — to identify patients with actionably low EF (40% or lower).

The AI model performed well, achieving an area under the receiver operating characteristic curve (AUROC) of 0.85, with 77.5% sensitivity and 78.3% specificity.

AI-powered screening for early detection

Heart failure with reduced ejection fraction (HFrEF) is often diagnosed late due to its subtle, non-specific symptoms. The AI model is designed to assist clinicians by identifying patients with potential cardiac dysfunction earlier in their disease progression.

“Early detection of left ventricular dysfunction is crucial, as delayed diagnosis often leads to worse patient outcomes and higher health care costs,” said Salima Qamruddin, MD, MPH, FASE, senior author of the study and technical director of the echocardiography laboratory at Ochsner Medical Center. “This study demonstrates how AI-enhanced digital stethoscope technology may serve as a powerful tool in identifying patients with potential heart failure earlier, enabling clinicians to take proactive steps in patient management.”

The study found that, among individuals flagged by the AI model as having low EF, but whose echocardiograms measured above 40%, 25% had EF values ranging from 41% to 49%, while 63% exhibited conduction or rhythm abnormalities. This suggests that the AI model can identify patients with high cardiovascular risk, even if they don’t meet traditional diagnostic thresholds.

Integrating AI-assisted cardiac assessments into routine physical exams and screenings could help primary care physicians identify at-risk patients earlier, expediting specialist referrals.

“The study findings highlight the promise of Eko’s platform to complement traditional diagnostics and address the critical challenge of underdiagnosed heart failure,” said Connor Landgraf, CEO, Eko Health. “By integrating AI-driven insights into routine physical exams, we can help clinicians identify at-risk patients sooner, particularly in primary care and resource-limited settings.”

This study builds on prior research into Eko Health’s AI-assisted cardiovascular screening technology.

A study published last month in the Journal of the American Heart Association (JAHA) highlighted the AI model’s ability to detect pulmonary hypertension (PH) by analyzing heart sounds. The model — which analyzes key acoustic markers, including changes in the second heart sound and tricuspid valve regurgitation murmurs to detect PH — achieved an AUROC of 0.79, with a sensitivity of 71% and specificity of 73%, demonstrating the growing potential of AI-enhanced auscultation in cardiopulmonary diagnostics.

Although traditional echocardiography remains the gold standard for diagnosing reduced EF, accessibility concerns have fueled the push for alternatives. AI-powered digital stethoscopes, like those from Eko Health, offer a non-invasive, scalable alternative for use in primary care settings to screen patients in real-time.