FDA Clears Tool to Aid in Identifying Patients With Low Ejection Fraction

The Food and Drug Administration (FDA) has cleared the Eko Low Ejection Fraction Tool (ELEFT), an algorithm intended to aid clinicians in identifying individuals 18 years and older with left ventricular ejection fraction (LVEF) less than or equal to 40%.

Developed with Mayo Clinic, the software uses signal processing, as well as algorithms derived from machine learning, to analyze 15 seconds of electrocardiogram (ECG) and heart sound data acquired through an Eko smart stethoscope to provide clinical decision support. It is intended for use on patients at risk for heart failure (eg, patients with coronary artery disease, diabetes mellitus, cardiomyopathy, hypertension and obesity).

The FDA clearance was based on data from a prospective clinical study of 3456 patients (median age, 64 years; 44.3% female). All participants underwent echocardiography within a maximum of 7 days of the corresponding ECG and heart sound recordings. True ejection fraction status was obtained by the echocardiogram machine’s integrated cardiac quantification software and was confirmed by a cardiologist. 

Of the 3456 recordings, 307 were excluded from the analysis due to poor ECG quality. A total of 341 cases of low EF were identified (prevalence 9.9%). Findings showed the sensitivity of ELEFT for detecting low EF was 74.7% (95% CI, 69.4-79.6); specificity was 77.5% (95% CI, 75.9-79.0).

“The ability to identify a hidden, potentially life-threatening heart condition using a tool that primary care and subspecialist clinicians are familiar with, the stethoscope, can help us prevent hospitalizations and adverse events,” said Dr Paul Friedman, Chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester. “Importantly, since a stethoscope is small and portable, this technology can be used in urban and remote locations, and hopefully help address care in underserved areas.”

According to Eko, the low EF detection AI will be added to the Company’s SENSORA Cardiac Early Detection Platform, which already includes algorithms to identify atrial fibrillation and structural heart murmurs. Positive results should be followed up with a cardiology consult or echocardiogram to confirm the presence or absence of low EF.