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

The stethoscope is an iconic medical instrument nearly synonymous with Western medicine. It is easy to handle, inexpensive, and its use is universally accepted-even expected-as part of a physical examination. Yet for the stethoscope to be a useful tool, it requires that the provider both captures and correctly interprets the diagnostic sounds of the patient. Though nearly all providers can perform the act of auscultation with minimal training, interpretation of the collected data is difficult, even for experienced and specialized providers. Inter-observer reliability for identification of a classic auscultatory finding -the "murmur" -is fair at best 1,2 , and the provider's ability to identify the true pathology underlying that finding is even worse 3 . Moreover, these challenges are further exacerbated by a noisy and rushed environment, which is the norm in modern practice. Despite the paucity of data in this area, anecdotally, these conclusions ring true for a wide spectrum of medical providers. Since cardiac auscultation remains a cornerstone of the physical exam, diagnostic assistance of its interpretation could therefore be of great use.