March 3, 2025 — Eko Health has published a peer-reviewed study in JACC Advances evaluating its FDA-cleared AI model for detecting reduced ejection fraction (EF), a common marker of a weakened heart that can't pump blood effectively (also known as heart failure with reduced ejection fraction, HFrEF). The study assessed the model's ability to analyze heart sound and single-lead electrocardiogram (ECG) data recorded via a digital stethoscope to identify individuals with actionably low EF (EF≤40%).
The study underscores the potential of Eko's non-invasive, scalable technology to aid in earlier identification of heart failure, especially in settings where advanced diagnostic tools like echocardiography are not readily available. Heart failure is often diagnosed late, frequently in acute settings where symptoms have already advanced significantly. Because its symptoms can be subtle and non-specific, many cases go unrecognized until significant deterioration has occurred. The AI model is optimally used in patients who present with non-specific symptoms such as unexplained dyspnea, where it can support fast access to diagnostic testing and treatment.
"Early detection of left ventricular dysfunction is crucial, as delayed diagnosis often leads to worse patient outcomes and higher healthcare costs," said Dr. Salima Qamruddin, senior author, Technical Director Echocardiography laboratory, Ochsner Medical Center, and Director Women's Cardiovascular Clinic, Ochsner Heart and Vascular Institute. "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."
Effective therapies for HFrEF exist and have been proven to improve patient outcomes when initiated early. By leveraging AI-powered heart sound and ECG analysis, clinicians may gain additional insights to support timely specialist referrals, further diagnostic evaluation, and better disease management. Real-world use of Eko's AI in an Imperial College London deployment demonstrated its potential to help identify patients at higher risk of adverse cardiac events and support earlier intervention.
"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 of 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."
Study Highlights AI's Role in Early Detection
The study enrolled 2,960 adults from four U.S. healthcare networks undergoing echocardiography. Researchers captured patient data using Eko's ECG-enabled digital stethoscope, ensuring echocardiograms were performed within one week of data collection. The AI model was evaluated against echocardiographic EF measurements, categorizing patients into two groups: normal/mildly reduced EF (>40%) and moderate/severely reduced EF (≤40%).
The AI model demonstrated strong predictive performance, achieving an AUROC of 0.85, with sensitivity and specificity of 77.5% and 78.3%, respectively. Among individuals flagged by the AI as potentially having low EF but whose echocardiograms showed EF >40%, 25% had an EF between 41-49%, and 63% had conduction or rhythm abnormalities, suggesting the AI model's potential role in identifying patients who may still be at cardiovascular risk. Performance was consistent across various demographic and clinical subgroups, reinforcing its broad applicability in clinical settings.
For more information, please visit www.ekohealth.com.
November 10, 2021 
