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

Eko's heart murmur detection algorithm has been approved for FDA 510(k) clearance 20 and is integrated with the Eko digital stethoscope and ECG software platform to assess single heart sound recordings. The algorithm was trained on recordings from a HIPAA-compliant collection of 400,000 audio recordings from Eko CORE and DUO electronic stethoscopes. The training set consisted of 5,878 de-identified audio recordings totaling over 34 hours from 5,318 unique patients. Recordings were initially randomly selected from the first 60,000 recordings collected and then sub-selected to ensure sufficient murmur examples to train the model. The training data quality is thus representative of what we expect in actual clinical use. The test set recordings used to measure classification performance of the trained algorithm are entirely separate and collected specifically for this purpose.