A Deep Learning Algorithm for Automated Cardiac Murmur Detection Via a Digital Stethoscope Platform

John S Chorba; Avi M Shapiro; Le Le; John Maidens; John Prince; Steve Pham; Mia M Kanzawa; Daniel N Barbosa; Brent E White; Jason Paek; Sophie G Fuller; Grant W Stalker; Sara A Bravo; Dina Jean; Subramaniam Venkatraman; Patrick M McCarthy; James D Thomas

Echocardiography remains the gold standard for diagnosis of VHD, given its minimal physical risk and excellent test characteristics 11 . Yet echocardiography requires both highly trained sonographers to acquire the data, as well as interpretation of the images by trained cardiologists. Accordingly, echocardiography is expensive, with the total annual cost of $1.2B for Medicare enrollees alone 12 . Despite its widespread use, it also requires a pre-existing suspicion from the referring provider, and it may not be locally available for patients in medically underserved areas. Because VHD is associated with textbook auscultatory findings 13 , cardiac auscultation can be a widespread, fast, and inexpensive tool to improve access to VHD screening, facilitate earlier detection of VHD, and reduce the need for unnecessary echocardiography. To begin to address this problem, we investigated the utility of an electronic stethoscope platform to develop a deep learning algorithm to identify cardiac murmurs.