Detection of Heart Conditions Using Artificial Intelligence

Real-World Evaluation of the Performance of Eko's Heart Murmur Detection Algorithm When Used by Front-line Healthcare Providers on Geriatric Patients

The purpose of this study is to evaluate how Eko AI performs in the real world, front-line setting where the availability of sophisticated, expensive diagnostic tools is limited, and where there is a premium on detecting VHD early in its course.

Study Overview

• Status: Completed
• Conditions: Heart Failure; Left Ventricular Dysfunction
• Intervention / Treatment: Device: Use of Eko DUO electronic stethoscope

Detailed Description

Echocardiography is the state of the art for diagnosing VHD. However, without an effective pre-screening tool, many echocardiograms ("echos") are being ordered unnecessarily. A recent study found that greater than 66% of all echos performed in the United States do not alter clinical management, while an additional 4% may be deemed inappropriate altogether.

Because of this, echos now make up a disproportionately large segment of healthcare expenditure. Each year, 1 in 5 Medicare enrollees receives an echo at a total cost of $1.2 billion, or 11% of total Medicare spending on imaging services. This is compounded by the fact that an estimated 35 million Americans live in medically underserved areas, where patients must travel an average of 56 miles to see a specialist and receive an echo. This does not encourage compliance, and only adds to cost, lost working hours, and inconvenience.

There is therefore a growing, unmet need for better VHD screening tools. Tools that will consistently, reliably, quickly, and cheaply identify VHD when it is early and asymptomatic, when patients can be managed early and appropriately, and when they are at the lowest risk from an intervention. Such a tool will have a positive impact on the cost of care, patient and provider experience, and healthcare outcomes.

The FDA-cleared Eko CORE and Eko DUO electronic stethoscopes offer clinicians a familiar and inexpensive tool that is widely accepted by patients and providers, while at the same time offer sensors and artificial intelligence technology that can improve screening and detection of medical conditions such as VHD. Both the CORE and the DUO feature sound amplification during auscultation - the CORE also offers active noise cancellation - which improves the ability of the clinician to detect nuanced changes in heart sounds.

• Study Type: Observational
• Enrollment (Actual): 68

Contacts and Locations

Study Locations

• United States
  • New York
    • New Hyde Park, New York, United States, 11040
      • Parker Jewish Institute of Health Care and Rehabilitation

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 18 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: N/A
• Genders Eligible for Study: All

• Sampling Method: Non-Probability Sample

Study Population

Patients undergoing a transthoracic echocardiogram will be enrolled. Patients who are over the age of 60 or who are at risk for heart failure (hypertension, murmur, etc.) will be targeted for enrollment. We will also target patients with a referral diagnosis of dyspnea on exertion, orthopnea, lower extremity edema, and possible heart failure.

Description

Inclusion Criteria:

• English-speaking adults who are 18 years and older
• Able and willing to provide informed consent
• Complete a clinical echocardiogram within 7 days before or after study procedures

Exclusion Criteria:

• Unwilling or unable to provide informed consent
• Patients who are hospitalized

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Cross-Sectional

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Single-lead ECG based algorithm development	Evaluate performance of single-lead ECG based algorithm to identify individuals with reduced ejection fraction.	Within two minutes of device use
Single-lead ECG based algorithm Performance	To demonstrate that Eko's murmur detection algorithm outperforms front-line healthcare providers in detecting heart murmurs in real-world use. Collecting data in a point-of-care setting will demonstrate how accurately the algorithm detects murmurs in comparison to an unassisted clinical examination. Algorithm output and clinical determination will be confirmed by echocardiographic ground truth, with the results being blinded until the end of the study	Within two minutes of device use

Collaborators and Investigators

• Sponsor: Eko Devices, Inc.

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2021
• Primary Completion (Actual): December 31, 2021
• Study Completion (Actual): December 31, 2021

Study Registration Dates

• First Submitted: June 14, 2021
• First Submitted That Met QC Criteria: June 14, 2021
• First Posted (Actual): June 22, 2021

Study Record Updates

• Last Update Posted (Estimate): December 9, 2022
• Last Update Submitted That Met QC Criteria: December 7, 2022
• Last Verified: December 1, 2022

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Heart Diseases; Cardiovascular Diseases; Ventricular Dysfunction; Ventricular Dysfunction, Left
• Other Study ID Numbers: 2021.5

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: No

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No