Handheld Wireless Digital Phonocardiography for Machine Learning-Based Detection of Mitral Regurgitation

Summary: Read research presented and published at the American Heart Association Scientific Sessions.
Handheld Wireless Digital Phonocardiography for Machine Learning-Based Detection of Mitral Regurgitation

Authors: Brent E White, Northwestern Memorial Hosp, Chicago, IL; Avi M Shapiro, Mia M Kanzawa, Subramaniam Venkatraman, Eko Devices, Inc., Berkeley, CA; Jason Paek, Northwestern Memorial Hosp, Chicago, IL; Steve Pham, John Maidens, Eko Devices, Inc., Berkeley, CA; James D Thomas, Patrick M McCarthy, Northwestern Memorial Hosp, Chicago, IL

Disclosures: B.E.White: Other - Consultant; Modest; Eko Devices, Inc.. A.M.Shapiro: Employment; Significant; Eko. M.M.Kanzawa: Employment; Significant; Eko Health. S.Venkatraman: None. J.Paek: Other - Consultant/advisor; Modest; Eko Devices, Inc.. S.Pham: Employment; Significant; Eko, Ownership Interest; Modest; Carbon Health. J.Maidens: Employment; Significant; Eko Devices, Inc.. J.D.Thomas: Honoraria; Modest; Edwards, Bay Labs, Other - Spouse employment; Significant; Bay Labs, Research Grant; Modest; Abbott, GE. P.M.Mccarthy: Honoraria; Modest; Atricure, Medtronic, Other - Advisory Board; Modest; Abbott, Other - Royalties; Consulting; Significant; Edwards Lifesciences.

Abstract/Background: Mitral regurgitation (MR) is a common disease which can be detected as a murmur on auscultation, but studies show that the majority of new primary care physicians do not detect MR murmurs which are confirmed by transthoracic echocardiography (TTE). The FDA-approved Eko CORE device is a digital stethoscope wirelessly paired with the Eko mobile application to allow recording and analysis of phonocardiograms (PCG). These PCG data drive a machine learning-based detection algorithm to identify clinically significant MR, validated by TTE, as part of the ongoing Phono- and Electrocardiogram Assisted Detection of Valvular Disease (PEA-Valve) Study.

Methods: Patients undergoing TTE at Northwestern Medicine underwent PCG recording by the Eko CORE device. Recordings 15 seconds long were obtained at 4 standard auscultation positions. A TensorFlow-based machine learning algorithm assessed the presence or absence of murmur with dominant localization to the cardiac apex indicating clinically significant MR, defined as moderate or greater on TTE.

Results: To date, 234 patients with 626 recordings have been enrolled, with 32 patients (13.7%) found to have significant MR on TTE. The receiver-operating characteristic curve had an area of 0.764, yielding a sensitivity of 61.5% (95% CI, 42.9-80.0%) and a specificity of 86.3% (95% CI, 76.5-94.7%) for the detection of MR.

Conclusion: PCG assessment using the Eko CORE device and machine learning interpretation is a fast and effective method to screen for significant MR and should be validated in a primary care setting.

View Research -->

Please note: Murmur detection is part of Eko’s SENSORA™ Cardiac Disease Detection Platform. Contact our sales team to learn more.