Phono- and Electrocardiogram Assisted Detection of Valvular Disease

Summary

The diagnosis of valvular heart disease (VHD), or its absence, invariably requires cardiac imaging. A familiar and inexpensive tool to assist in the diagnosis or exclusion of significant VHD could both expedite access to life-saving therapies and reduce the need for costly testing. The FDA-approved Eko Duo device consists of a digital stethoscope and a single-lead electrocardiogram (ECG), which wirelessly pairs with the Eko Mobile application to allow for simultaneous recording and visualization of phono- and electrocardiograms. These features uniquely situate this device to accumulate large sets of auscultatory data on patients both with and without VHD.

In this study, the investigators seek to develop an automated system to identify VHD by phono- and electrocardiogram. Specifically, the investigators will attempt to develop machine learning algorithms to learn the phonocardiograms of patients with clinically important aortic stenosis (AS) or mitral regurgitation (MR), and then task the algorithms to identify subjects with clinically important VHD, as identified by a gold standard, from naïve phonocardiograms. The investigators anticipate that the study has the potential to revolutionize the diagnosis of VHD by providing a more accurate substitute to traditional auscultation.

Conditions

• Aortic Valve Stenosis
• Mitral Regurgitation
• Heart Murmurs
• Valvular Heart Disease

Interventions

DIAGNOSTIC_TEST

AS Algorithm 1

Machine learning algorithm, generated from ECG and PCG recordings, distinguishing moderate-to-severe or greater aortic stenosis from controls having structurally normal hearts with no greater than mild valvular heart disease at any location.

DIAGNOSTIC_TEST

AS Algorithm 2

Machine learning algorithm, generated from ECG and PCG recordings, distinguishing moderate-to-severe or greater aortic stenosis from controls having any findings other than moderate-to-severe or greater aortic stenosis.

DIAGNOSTIC_TEST

MR Algorithm 1

Machine learning algorithm, generated from ECG and PCG recordings, distinguishing moderate-to-severe or greater mitral regurgitation from controls having structurally normal hearts with no greater than mild valvular heart disease at any location.

DIAGNOSTIC_TEST

MR Algorithm 2

Machine learning algorithm, generated from ECG and PCG recordings, distinguishing moderate-to-severe or greater mitral regurgitation from controls having any findings other than moderate-to-severe or greater mitral regurgitation.

Sponsors & Collaborators

• Eko Devices, Inc.

  collaborator INDUSTRY

• University of California, San Francisco

  lead OTHER

Principal Investigators

• John Chorba, MD · University of California, San Francisco

Eligibility

Min Age

18 Years

Sex

ALL

Healthy Volunteers

Yes

Timeline & Regulatory

Start

2018-02-22

Primary Completion

2019-11-11

Completion

2019-11-11

FDA Device

Yes

Countries

• United States

Study Locations