AI-Enabled Direct-from-ECG Ejection Fraction (EF) Severity Assessment Using COR ECG Wearable Monitor

NCT06699056 | Recruiting DMC FDA Device

• 1 other identifier: PBH-COREFS-1-A
• Study Type: observational
• Target: 1,500
• Locations: 1 country
• Sites: 8

Brief Summary

This prospective, multicenter, cluster-randomized controlled study aims to evaluate the accuracy of an investigational artificial intelligence (AI) Software as a Medical Device (SaMD) designed to compute ejection fraction (EF) severity categories based on the American Society of Echocardiography's (ASE) 4-category scale. The software analyzes continuous ECG waveform data acquired by the FDA-cleared Peerbridge COR® ECG Wearable Monitor, an ambulatory patch device designed for use during daily activities. The AI software assists clinicians in cardiac evaluations by estimating EF severity, which reflects how well the heart pumps blood. In this study, EF severity determination will be made using 5-minute ECG recordings collected during a 15-minute resting period with participants seated upright. The results will be compared to EF severity obtained from an FDA-cleared, non-contrast transthoracic echocardiogram (TTE) predicate device. This comparison aims to validate the accuracy of the AI software.

Conditions

Ventricular Ejection Fraction; LVF; LV Dysfunction; Atrial Enlargement; Conduction Defect; Heart Failure; Valvular Heart Disease; Ischemic Heart Disease; Cardiotoxicity; Myocardial Infarction; Dilated Cardiomyopathy; HFrEF - Heart Failure With Reduced Ejection Fraction; HFpEF - Heart Failure With Preserved Ejection Fraction; Syncope; Remodeling, Cardiac

Keywords

ECG Patch; LVEF; Holter; ECG Wearable; COR; Atrial Conduction; ECG Biomarker; LV Dysfunction; SaMD; Clinical Decision Support; ECG; EF Severity; Ejection Fraction; AI; Atrial Enlargement; Electrical Remodeling

Outcome Measures

Primary Outcomes (1)

• Agreement of CorEFS Software EF Severity Categories Using Peerbridge COR™ ECG Data with ASE EF Severity Categories Established by Ultrasound Echocardiography

  The primary endpoint of this trial is to demonstrate substantial agreement between EF severity categories determined by the CorEFS Software using 5 minutes of Peerbridge COR™ ECG data and the subject's EF severity category established through ultrasound echocardiography, the gold standard for EF classification. The study includes four co-primary endpoints, representing agreement measures within each of the four EF severity categories defined by the American Society of Echocardiography (ASE) Scale (Normal, Mildly Abnormal, Moderately Abnormal, Severely Abnormal). For each category the endpoint is the proportion of participants correctly classified by the test device relative to the reference standard. The goal is to demonstrate at least 80% agreement within each EF severity category.

  Through study completion, average of 9 months.

Secondary Outcomes (1)

• Confirmation of ≥80% Agreement Between Peerbridge Cor™ ECG Data and Reference Standard ECHO in EF Severity Categorization Using 15-Minute Continuous Monitoring: Secondary Endpoint Analysis

  Through study completion, average of 9 months.

Other Outcomes (1)

• Substantial Equivalence of Peerbridge Cor™ ECG-Derived EF Severity Results Across 2-Minute, 5-Minute, and 15-Minute Time Windows Compared to Reference Standard ECHO

  Through study completion, average of 9 months.

Study Arms (1)

Cohort Breakdown to Power Accuracy Assessments

The study will enroll up to 1,500 participants across Subprotocol A and B, with a predictive total cohort of at least 660 unique participants. Each participant must provide at least one valid paired data point, defined as ECHO results paired with at least 30 minutes of Peerbridge COR™ ECG data, acquired concurrently or within 60 minutes of ECHO completion. Enrollment will occur at a minimum of 3 trial sites, with data collection ensuring at least 165 valid paired points per EF Severity category, as determined by the reference ECHO, from different participants. A paired data point is considered invalid if all 5-minute sitting windows during a 15-minute session yield "Not Analyzable" outputs. Participants who do not comply with the protocol or do not yield valid paired data points will be excluded from analysis and study statistics. Trial site investigators may use institutional EMR databases to identify, qualify, and recruit participants from their community patient populations.

Device: 15-minutes of sitting during COR ECG Acquistion

Interventions

15-minutes of sitting during COR ECG Acquistion DEVICE

Participants will follow a standardized protocol during a 15-minute seated session using the Peerbridge COR™ device. Participants will sit comfortably in an upright chair with a straight back; armrests are optional. Their feet must remain flat on the floor with legs uncrossed to ensure unobstructed blood flow and a stable posture. Arms should be relaxed and placed in their lap, on a flat surface (e.g., table), or on the armrest, ensuring they are not tensed or elevated. Participants will maintain a straight back with relaxed shoulders throughout the session. To begin, participants will press the Event Button on the Peerbridge COR™ mobile device, marking the start of the session. They will remain seated in this position for 15 minutes. At the end of the session, participants will press the Event Button again to mark the conclusion of the seated event. This protocol ensures consistent data collection across all participants.

Cohort Breakdown to Power Accuracy Assessments

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Participants will be recruited from the community population receiving treatments or affiliated with participating trial sites. These sites will include hospitals, cardiac/medical/academic research centers, and medical practice clinics. It is anticipated that 6 to 15 trial sites distributed across the United States will participate in the study. Enrollment will aim to include participants across all four ASE Ejection Fraction Severity Categories to ensure sufficient statistical power for accuracy assessment. The study population will comprise both male and female participants, as ASE Ejection Fraction Severity category thresholds differ by gender.

You may qualify if:

• Age ≥ 18 years
• Able and eligible to wear a Holter monitor

You may not qualify if:

• Receiving mechanical respiratory or circulatory support, or renal support therapy, at the time of screening or during Visit #1
• Any condition that, in the investigator's opinion, could interfere with compliance with the study protocol or pose a safety risk to the participant
• History of poor tolerance or severe skin reactions to ECG adhesive materials

Sponsors & Collaborators

• Peerbridge Health, Inc: lead

Study Sites (8)

Orange County Heart Institute

Orange, California, 92868, United States

RECRUITING

Peerbridge Health

Melbourne, Florida, 32935, United States

NOT YET RECRUITING

Henry Ford Hospital

Detroit, Michigan, 48202, United States

RECRUITING

Hackensack University Medical Center

Hackensack, New Jersey, 07601, United States

RECRUITING

Mount Sinai Hospital

New York, New York, 10019, United States

RECRUITING

Moses H. Cone Memorial Hospital

Greensboro, North Carolina, 27401, United States

RECRUITING

Texas Cardiac Arrhythmia Research Foundation

Austin, Texas, 78705, United States

RECRUITING

South Heart Clinic

Weslaco, Texas, 78596, United States

RECRUITING

Related Publications (11)

• Murtagh G, Dawkins IR, O'Connell R, Badabhagni M, Patel A, Tallon E, O'Hanlon R, Ledwidge MT, McDonald KM. Screening to prevent heart failure (STOP-HF): expanding the focus beyond asymptomatic left ventricular systolic dysfunction. Eur J Heart Fail. 2012 May;14(5):480-6. doi: 10.1093/eurjhf/hfs030. Epub 2012 Mar 13.

  PMID: 22416086 BACKGROUND

• Lang RM, Badano LP, Mor-Avi V, Afilalo J, Armstrong A, Ernande L, Flachskampf FA, Foster E, Goldstein SA, Kuznetsova T, Lancellotti P, Muraru D, Picard MH, Rietzschel ER, Rudski L, Spencer KT, Tsang W, Voigt JU. Recommendations for cardiac chamber quantification by echocardiography in adults: an update from the American Society of Echocardiography and the European Association of Cardiovascular Imaging. J Am Soc Echocardiogr. 2015 Jan;28(1):1-39.e14. doi: 10.1016/j.echo.2014.10.003.

  PMID: 25559473 BACKGROUND

• Alhamaydeh M, Gregg R, Ahmad A, Faramand Z, Saba S, Al-Zaiti S. Identifying the most important ECG predictors of reduced ejection fraction in patients with suspected acute coronary syndrome. J Electrocardiol. 2020 Jul-Aug;61:81-85. doi: 10.1016/j.jelectrocard.2020.06.003. Epub 2020 Jun 5.

  PMID: 32554161 BACKGROUND

• O'Neal WT, Mazur M, Bertoni AG, Bluemke DA, Al-Mallah MH, Lima JAC, Kitzman D, Soliman EZ. Electrocardiographic Predictors of Heart Failure With Reduced Versus Preserved Ejection Fraction: The Multi-Ethnic Study of Atherosclerosis. J Am Heart Assoc. 2017 May 25;6(6):e006023. doi: 10.1161/JAHA.117.006023.

  PMID: 28546456 BACKGROUND

• Chen HY, Lin CS, Fang WH, Lou YS, Cheng CC, Lee CC, Lin C. Artificial Intelligence-Enabled Electrocardiography Predicts Left Ventricular Dysfunction and Future Cardiovascular Outcomes: A Retrospective Analysis. J Pers Med. 2022 Mar 13;12(3):455. doi: 10.3390/jpm12030455.

  PMID: 35330455 BACKGROUND

• Adedinsewo D, Carter RE, Attia Z, Johnson P, Kashou AH, Dugan JL, Albus M, Sheele JM, Bellolio F, Friedman PA, Lopez-Jimenez F, Noseworthy PA. Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea. Circ Arrhythm Electrophysiol. 2020 Aug;13(8):e008437. doi: 10.1161/CIRCEP.120.008437. Epub 2020 Aug 4.

  PMID: 32986471 BACKGROUND

• Yao X, Rushlow DR, Inselman JW, McCoy RG, Thacher TD, Behnken EM, Bernard ME, Rosas SL, Akfaly A, Misra A, Molling PE, Krien JS, Foss RM, Barry BA, Siontis KC, Kapa S, Pellikka PA, Lopez-Jimenez F, Attia ZI, Shah ND, Friedman PA, Noseworthy PA. Artificial intelligence-enabled electrocardiograms for identification of patients with low ejection fraction: a pragmatic, randomized clinical trial. Nat Med. 2021 May;27(5):815-819. doi: 10.1038/s41591-021-01335-4. Epub 2021 May 6.

  PMID: 33958795 BACKGROUND

• Sangha V, Nargesi AA, Dhingra LS, Khunte A, Mortazavi BJ, Ribeiro AH, Banina E, Adeola O, Garg N, Brandt CA, Miller EJ, Ribeiro ALP, Velazquez EJ, Giatti L, Barreto SM, Foppa M, Yuan N, Ouyang D, Krumholz HM, Khera R. Detection of Left Ventricular Systolic Dysfunction From Electrocardiographic Images. Circulation. 2023 Aug 29;148(9):765-777. doi: 10.1161/CIRCULATIONAHA.122.062646. Epub 2023 Jul 25.

  PMID: 37489538 BACKGROUND

• Bachtiger P, Petri CF, Scott FE, Ri Park S, Kelshiker MA, Sahemey HK, Dumea B, Alquero R, Padam PS, Hatrick IR, Ali A, Ribeiro M, Cheung WS, Bual N, Rana B, Shun-Shin M, Kramer DB, Fragoyannis A, Keene D, Plymen CM, Peters NS. Point-of-care screening for heart failure with reduced ejection fraction using artificial intelligence during ECG-enabled stethoscope examination in London, UK: a prospective, observational, multicentre study. Lancet Digit Health. 2022 Feb;4(2):e117-e125. doi: 10.1016/S2589-7500(21)00256-9. Epub 2022 Jan 5.

  PMID: 34998740 BACKGROUND

• Al Younis SM, Hadjileontiadis LJ, Khandoker AH, Stefanini C, Soulaidopoulos S, Arsenos P, Doundoulakis I, Gatzoulis KA, Tsioufis K. Prediction of heart failure patients with distinct left ventricular ejection fraction levels using circadian ECG features and machine learning. PLoS One. 2024 May 13;19(5):e0302639. doi: 10.1371/journal.pone.0302639. eCollection 2024.

  PMID: 38739639 BACKGROUND

• Garcia-Escobar A, Vera-Vera S, Jurado-Roman A, Jimenez-Valero S, Galeote G, Moreno R. Subtle QRS changes are associated with reduced ejection fraction, diastolic dysfunction, and heart failure development and therapy responsiveness: Applications for artificial intelligence to ECG. Ann Noninvasive Electrocardiol. 2022 Nov;27(6):e12998. doi: 10.1111/anec.12998. Epub 2022 Jul 29.

  PMID: 35904538 BACKGROUND

MeSH Terms

Conditions

Ventricular Dysfunction, Left; Arrhythmias, Cardiac; Heart Failure; Heart Valve Diseases; Myocardial Ischemia; Cardiotoxicity; Myocardial Infarction; Cardiomyopathy, Dilated; Syncope; Atrial Remodeling

Condition Hierarchy (Ancestors)

Ventricular Dysfunction; Heart Diseases; Cardiovascular Diseases; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Vascular Diseases; Drug-Related Side Effects and Adverse Reactions; Chemically-Induced Disorders; Radiation Injuries; Wounds and Injuries; Infarction; Ischemia; Necrosis; Cardiomegaly; Cardiomyopathies; Laminopathies; Genetic Diseases, Inborn; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Unconsciousness; Consciousness Disorders; Neurobehavioral Manifestations; Neurologic Manifestations; Nervous System Diseases; Signs and Symptoms; Pathological Conditions, Anatomical

Study Officials

• Andrea Natale, MD

  Texas Cardiac Arrhythmia Research Foundation

  PRINCIPAL INVESTIGATOR

• Johanna P Contreras, MD

  MOUNT SINAI HOSPITAL

  PRINCIPAL INVESTIGATOR

• Sachin Parikh, MD

  Henry Ford Hospital

  PRINCIPAL INVESTIGATOR

• Brian Kolski, MD

  Orange County Heart Institute

  PRINCIPAL INVESTIGATOR

• Daniel Bensimhon, MD

  Moses H. Cone Memorial Hospital

  PRINCIPAL INVESTIGATOR

• Sandeep Gulati, PhD

  Peerbridge Health, Inc

  PRINCIPAL INVESTIGATOR

• Frank Mazzola, MD

  South Heart Clinic

  PRINCIPAL INVESTIGATOR

• Sameer Jamal, MD

  Hackensack Meridian Health

  PRINCIPAL INVESTIGATOR

Central Study Contacts

Sandeep Gulati, PhD

CONTACT

8182162958; s.gulati@peerbridgehealth.com

Chris Darland, MBA

CONTACT

814-572-7138; c.darland@peerbridgehealth.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 15, 2024
• First Posted: November 21, 2024
• Study Start: November 21, 2024
• Primary Completion: September 1, 2025
• Study Completion: September 1, 2025
• Last Updated: February 11, 2025

Record last verified: 2025-02

Data Sharing

• IPD Sharing: Will share
• Shared Documents: STUDY PROTOCOL, SAP, ICF, CSR
• Time Frame: 60 days after Trial Scoring is Completed. Expected Around July/Aug 2025. Will be available for 3 years after the date.
• Access Criteria: Trial Site PI, Sub-Investigators, Trial Site Research Staff, Trial Site Affiliates, Data Safety Monitoring Board (DSMB)Members, KOLs invited to Data Reviews and Affiliates; Publication submissions sites if required.

Locations

US (8)