Real-World Evaluation of Eko Murmur Analysis Software in a Point of Care Setting

The purpose of this research is to evaluate the impact of Eko AI plus EMAS (Eko Murmur Analysis Software) on a clinician's referral decision in a real-world primary care setting. There is an additional objective of understanding patient outcomes when patients are referred for cardiology follow-up and/or echocardiogram.

Study Overview

• Status: Recruiting
• Conditions: Heart Murmurs; Murmur, Heart; Innocent Murmurs; Pathologic Murmur
• Intervention / Treatment: Device: Use of Eko CORE electronic stethoscope

Detailed Description

Eko has developed a platform to aid in screening for cardiac conditions using a digital stethoscope and machine-learning algorithms to detect the presence or absence of heart conditions such as heart murmurs and atrial fibrillation. In June 2022, the US Food and Drug Administration (FDA) granted Eko a 510(k) clearance for the marketing of "Eko Murmur Analysis Software" (EMAS), a set of machine learning algorithms that are able to screen signal quality and identify fundamental heart sounds, distinguish structural murmurs from absent or innocent murmurs, and provide a structural murmur's timing in the cardiac cycle.

This study sets out to evaluate the impact of EMAS on a clinician's referral decision in a real-world primary care setting, with the additional objective of understanding patient outcomes when patients are referred for cardiology follow-up and/or echocardiogram. Providers will receive access to the EMAS screening tool, called the SENSORA™ Disease Detection Platform, which features the FDA cleared 3M™ Littmann® CORE stethoscope paired with the FDA cleared SENSORA™ enterprise application and EMAS AI running on an iPad, which is mounted on a Tryten stand. SENSORA™ will be used by medical assistants or equivalent as part of the initial patient intake process (e.g., during vitals acquisition).

EMAS influence on individual providers will be assessed by reviewing each provider's number of referrals to cardiology and number of echocardiogram orders for the 6 months preceding study start. These values will be compared to cardiac referral and order rates at the end of the study. Patient outcomes data (e.g., cardiology appointment notes, echocardiogram findings, follow up visits scheduled) will be pulled 6 months after the patient is seen by their primary care provider. Secondary objectives include the continued assessment of algorithm performance on a point-of-care population.

• Study Type: Observational
• Enrollment (Estimated): 1200

Contacts and Locations

• Study Contact: Name: Cody Hitchcock, MSc; Phone Number: 1-844-356-3384; Email: cody.hitchcock@ekohealth.com

Study Locations

• United States
  • District of Columbia
    • Washington, District of Columbia, United States, 20010
      • Recruiting
      • MedStar Washington Hospital Center
      • Contact: Theresa Moriarty, MSN, RN
      • Principal Investigator: Arrel Olano, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: 55 years and older (Adult, Older Adult)
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

Potential research subjects will be screened by MedStar study personnel for eligibility from the onsite primary, internal medicine, and geriatric clinics at MedStar. If a patient meets all of the inclusion criteria, and none of the exclusion criteria, they will be approached for participation.

Description

Inclusion Criteria:

• Patient verbally consents to participation
• Patient is willing to have heart sounds recorded with an electronic stethoscope
• Patient is age 50 years or older

Exclusion Criteria:

• Patient is unwilling or unable to give verbal informed consent
• Patients experiencing a known or suspected acute cardiac event
• Patient is under the age of 50 years old

Study Plan

How is the study designed?

Design Details

• Observational Models: Cohort
• Time Perspectives: Prospective

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Prospective cohort; Patients who are at least 50 years of age during their primary care exam will undergo SENSORA™ screening if they provide consent.	Device: Use of Eko CORE electronic stethoscope; Recording of heart sounds using electronic stethoscope
Retrospective cohort; Patients who saw participating providers in the 6 months prior to study start date, and who were referred to echocardiogram and/or cardiology, will be included as provider self-control for patient outcomes and referral rates.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Impact of EMAS on echocardiogram order rates	Echocardiogram order rates before and after SENSORA implementation, for individual providers and aggregated for the site as a whole	01/17/2022 - 11/30/2023
Impact of EMAS on cardiologist consult order rates	Cardiology consultation referral rates before and after SENSORA implementation, for individual providers and aggregated for the site as a whole	01/17/2022 - 11/30/2023
Impact of EMAS on provider decision-making	Impact of EMAS on provider decision to refer to echocardiogram, cardiologist, or other workup related to cardiac murmur. Measured via a survey administered to each provider after each patient is screened, which asks if SENSORA AI influenced their decision to refer or not to refer. Measured for individual providers and aggregated for the site as a whole.	01/17/2022 - 11/30/2023

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Impact of EMAS on patient outcomes	VHD discovery rates before and after SENSORA platform implementation, for individual providers and aggregated for the site as a whole	01/17/2022 - 11/30/2023
Sensitivity and specificity	EMAS' accuracy (sensitivity and specificity) in detecting structural murmur, compared to an annotator panel	01/17/2022 - 11/30/2023

Collaborators and Investigators

• Sponsor: Eko Devices, Inc.

Study record dates

Study Major Dates

• Study Start (Actual): March 11, 2022
• Primary Completion (Estimated): November 1, 2023
• Study Completion (Estimated): November 1, 2023

Study Registration Dates

• First Submitted: December 15, 2021
• First Submitted That Met QC Criteria: December 15, 2021
• First Posted (Actual): January 4, 2022

Study Record Updates

• Last Update Posted (Actual): June 22, 2023
• Last Update Submitted That Met QC Criteria: June 20, 2023
• Last Verified: June 1, 2023

More Information

Terms related to this study

• Keywords: machine learning; artificial intelligence
• Additional Relevant MeSH Terms: Pathologic Processes; Heart Diseases; Cardiovascular Diseases; Arrhythmias, Cardiac; Heart Murmurs
• Other Study ID Numbers: 2021.12

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO
• IPD Plan Description: All participant data will be de-identified. Data will only be shared with Eko Devices, and not shared with any other researchers.

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No