Clinical Research

Handheld Wireless Digital Phonocardiography for Machine Learning-Based Detection of Aortic Stenosis

Learn how the CORE can more accurately detect aortic stenosis.
March 4, 2021

Authors: Brent E. White, Jason Paek, Steve Pham, John Maidens,Patrick M. McCarthy, and James D. Thomas

Background: Aortic stenosis (AS) is a common disease which can be detected as a murmur on auscultation, but studies show that up to 80% of new primary care physicians do not detect AS 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 learningbased detection algorithm to identify clinically significant AS, 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 COREdevice. Recordings 15 seconds long were obtained at four standard auscultation positions (figure1). A TensorFlow-based machine learning algorithm assessed the presence or absence of murmur with dominant localization to the right upper sternal border indicating clinically significant AS (moderate or more on TTE).

Results: To date, 161 patients with 639 recordings have been enrolled, with 14 patients (8.7%) found tohave significant AS on TTE. The receiver-operating characteristic curve had an area of 0.964, yielding a sensitivity of 97.2% (95% CI, 84.7-99.5%) and a specificity of 86.4% (95% CI, 84.0-88.7%) for the detection of AS (figure 2).

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

Link to research -->