A Multicenter Pragmatic Implementation Study of ECG-AI-Based Clinical Decision Support Software to Identify Low LVEF

NCT05867407 | Terminated FDA Device

• 1 other identifier: DOC-244
• Study Type: interventional
• Target: 11,610
• Locations: 1 country
• Sites: 5

Brief Summary

A prospective, cluster-randomized, care-as-usual controlled trial to evaluate the impact of an ECG-based artificial intelligence (ECG-AI) algorithm to detect low left ventricular ejection fraction (LVEF) on diagnosis rates of LVEF ≤ 40% in the outpatient setting. The objective of this study is to evaluate the impacts of an ECG-AI algorithm to detect low LVEF and an associated Medical Device Data System when used during routine outpatient care. The study will be conducted in 2 phases: feasibility assessment phase and clinical impact phase.

Conditions

Ventricular Ejection Fraction

Outcome Measures

Primary Outcomes (1)

• Diagnosis rates of low ejection fraction of less than or equal to 40 percent by echocardiography compared to care-as-usual

  Diagnosis rates of low ejection fraction of less than or equal to 40 percent by echocardiography compared to care-as-usual

  90 days

Study Arms (2)

Anumana Low EF AI-ECG Algorithm

EXPERIMENTAL

Anumana Low EF AI-ECG Algorithm

Device: Anumana Low EF AI-ECG Algorithm

Care-as-Usual

OTHER

Care-as-Usual

Other: Care-as-Usual

Interventions

Anumana Low EF AI-ECG Algorithm DEVICE

Clinician will have access to the Anumana Low EF AI-ECG algorithm via a link in the patient's electronic health record which will display results applied to patients' ECGs, as well as supporting information. Using the results of the algorithm, combined with the clinician's knowledge of patient-specific risk factors, the clinician will determine whether further evaluation is warranted.

Anumana Low EF AI-ECG Algorithm

Care-as-Usual OTHER

Clinicians will not have access to the Anumana Low EF AI-ECG algorithm and will provide care-as-usual.

Care-as-Usual

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• Males and females 18 years or older (including females who are pregnant, breastfeeding and/or lactating)
• Digital ECG captured or available within site for ECG-AI analysis at point-of-care

You may not qualify if:

• Known history of LVEF ≤ 40%
• Known history of systolic heart failure
• Known history of heart failure with reduced ejection fraction
• Opted out of electronic health record-based research

Sponsors & Collaborators

• Anumana, Inc.: lead
• Mayo Clinic: collaborator

Study Sites (5)

Mayo Clinic Arizona

Phoenix, Arizona, 85054, United States

Location

Mayo Clinic Florida

Jacksonville, Florida, 32224, United States

Location

Mayo Clinic Rochester

Rochester, Minnesota, 55905, United States

Location

Duke Health

Durham, North Carolina, 27710, United States

Location

University of Texas Southwestern

Dallas, Texas, 75390, United States

Location

Related Publications (1)

• Lopez-Jimenez F, Alger HM, Attia ZI, Barry B, Chatterjee R, Dolor R, Friedman PA, Greene SJ, Greenwood J, Gundurao V, Hackett S, Jain P, Kinaszczuk A, Mehta K, O'Grady J, Pandey A, Pullins C, Puranik AR, Ranganathan MK, Rushlow D, Stampehl M, Subramanian V, Vassor K, Zhu X, Awasthi S. A multicenter pragmatic implementation study of AI-ECG-based clinical decision support software to identify low LVEF: Clinical trial design and methods. Am Heart J Plus. 2025 Mar 21;54:100528. doi: 10.1016/j.ahjo.2025.100528. eCollection 2025 Jun.

  PMID: 40276542 DERIVED

Study Officials

• Francisco Lopez-Jimenez, MD, MSc, MBA

  Mayo Clinic

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: NONE
• Purpose: SCREENING
• Intervention Model: PARALLEL
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Model Details: Clinicians in primary care practice groups will be consented for enrollment into the study. Practice groups that decide to participate in the study will be randomized to have the software available or to provide care as usual without the software.

Study Record Dates

• First Submitted: May 1, 2023
• First Posted: May 22, 2023
• Study Start: June 13, 2024
• Primary Completion: May 30, 2025
• Study Completion: May 30, 2025
• Last Updated: September 4, 2025

Record last verified: 2025-08

Data Sharing

• IPD Sharing: Will not share

Locations

US (5)