Eko Health's AI Model Enhances Early Detection of Heart Failure

Eko Health has published a study in the Journal of the American College of Cardiology (JACC) Advances, showcasing the potential of its AI model to detect reduced ejection fraction (EF), a critical marker of heart failure announced in a press release. The study evaluated the model's ability to analyze heart sound and single-lead ECG data using a digital stethoscope, identifying individuals with low EF (≤40%).

The research involved 2,960 adults from four U.S. healthcare networks, with data collected via Eko's ECG-enabled digital stethoscope. The AI model demonstrated strong predictive performance, achieving an AUROC of 0.85, with sensitivity and specificity of 77.5% and 78.3%, respectively. This indicates its potential to aid in early identification of heart failure, especially in settings lacking advanced diagnostic tools like echocardiography.

The study highlights the promise of Eko's platform to complement traditional diagnostics and address the challenge of underdiagnosed heart failure. By integrating AI-driven insights into routine exams, clinicians can identify at-risk patients sooner, particularly in primary care and resource-limited settings.