Deep Learning Algorithms to Detect Murmurs Associated With Structural Heart Disease

Summary: A study published in JAHA (Journal of the American Heart Association) reveals that Eko's FDA-cleared algorithms, trained on over 15,000 heart sound recordings, outperform clinicians. In real clinical environments, they demonstrate a sensitivity of 97.9% and specificity of 90.6% when detecting clearly audible murmurs in adults.
Journal of the American Heart Association (JAHA) cover

Authors: John Prince, John Maidens, Spencer Kieu, Caroline Currie, Daniel Barbosa, Cody Hitchcock, Adam Saltman, Kambiz Norozi, Philipp Wiesner, Nicholas Slamon, Erica Del Grippo, Deepak Padmanabhan, Anand Subramanian, Cholenahalli Manjunath, John Chorba and Subramaniam Venkatraman

Background: The success of cardiac auscultation varies widely among medical professionals, which can lead to missed treatments for structural heart disease. Applying machine learning to cardiac auscultation could address this problem, but despite recent interest, few algorithms have been brought to clinical practice. We evaluated a novel suite of Food and Drug Administration‐cleared algorithms trained via deep learning on >15 000 heart sound recordings.

Methods and results: We validated the algorithms on a data set of 2375 recordings from 615 unique subjects. This data set was collected in real clinical environments using commercially available digital stethoscopes, annotated by board‐certified cardiologists, and paired with echocardiograms as the gold standard. To model the algorithm in clinical practice, we compared its performance against 10 clinicians on a subset of the validation database. Our algorithm reliably detected structural murmurs with a sensitivity of 85.6% and specificity of 84.4%. When limiting the analysis to clearly audible murmurs in adults, performance improved to a sensitivity of 97.9% and specificity of 90.6%. The algorithm also reported timing within the cardiac cycle, differentiating between systolic and diastolic murmurs. Despite optimizing acoustics for the clinicians, the algorithm substantially outperformed the clinicians (average clinician accuracy, 77.9%; algorithm accuracy, 84.7%.)

Conclusions: The algorithms accurately identified murmurs associated with structural heart disease. Our results illustrate a marked contrast between the consistency of the algorithm and the substantial interobserver variability of clinicians. Our results suggest that adopting machine learning algorithms into clinical practice could improve the detection of structural heart disease to facilitate patient care.

View Research -->