AI-ECG Algorithm for Low Heart Function

(AIM ECG-AI Trial)

Recruiting at 5 trial locations

Overseen By Sarah Hackett

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Anumana, Inc.

Disqualifiers: LVEF ≤ 40%, Systolic heart failure, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

50198 Participants Needed

Trial Summary

Do I need to stop my current medications for this trial?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment Anumana Low EF AI-ECG Algorithm for low heart function?

Research shows that an AI-enabled ECG algorithm can effectively identify low heart function, with high accuracy, sensitivity, and specificity, making it a powerful screening tool for detecting heart issues early. ^{1 2 3 4 5}

Is the AI-ECG Algorithm for Low Heart Function safe for humans?

The AI-ECG algorithm is a tool used to analyze heart function through ECGs (electrocardiograms) and has been tested on large groups of patients to identify heart issues. It is a noninvasive method, meaning it doesn't involve surgery or entering the body, and is generally considered safe as it uses standard ECG data to help doctors detect heart problems early. ^{2 6 7 8 9}

How does the Anumana Low EF AI-ECG Algorithm treatment differ from other treatments for low heart function?

The Anumana Low EF AI-ECG Algorithm is unique because it uses artificial intelligence to analyze electrocardiograms (ECGs) and detect low heart function, specifically left ventricular dysfunction, in a non-invasive and cost-effective way. Unlike traditional methods, this AI-enhanced approach can identify heart issues that are often hidden or asymptomatic, providing an early warning system for potential heart problems. ^{2 5 10 11 12}

What is the purpose of this trial?

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.

Research Team

Francisco Lopez-Jimenez, MD, MSc, MBA

Principal Investigator

Mayo Clinic

Eligibility Criteria

This trial is for adults aged 18 or older who can have a digital 10-second, 12-lead ECG captured or available in their electronic health records (EHR) for AI analysis at the point-of-care.

Inclusion Criteria

Digital 10 second, 12 Lead ECG captured or available in EHR or ECG data store for AI-ECG analysis at point-of-care

Exclusion Criteria

Opted out of electronic health record-based research

Known history of LVEF ≤ 40%

I have a history of heart failure.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Feasibility Assessment

Feasibility pilot to evaluate integration and usability of the ECG-AI algorithm

6 weeks

Clinical Impact Observation

Observational period to evaluate clinical outcomes using the ECG-AI algorithm

3 months

Follow-up

Participants are monitored for safety and effectiveness after the observational period

90 days

Treatment Details

Interventions

• Anumana Low EF AI-ECG Algorithm

Trial Overview The study tests an AI-powered ECG algorithm designed to detect low left ventricular ejection fraction (LVEF), which indicates heart problems. It compares usual care with and without the use of this AI tool in outpatient settings.

Participant Groups

Group I: Care-as-Usual Experimental Treatment 1 Intervention

Care-as-Usual

Group II: Anumana Low EF AI-ECG Algorithm Experimental Treatment 1 Intervention

Anumana Low EF AI-ECG Algorithm

Who Is Running the Clinical Trial?

Anumana, Inc.

Lead Sponsor

Trials

2

Recruited

66,200+

Mayo Clinic

Collaborator

Trials

3,427

Recruited

3,221,000+

Findings from Research

A study involving 44,959 patients demonstrated that an AI model applied to ECG data can effectively identify asymptomatic left ventricular dysfunction (ALVD), achieving high accuracy (85.7%) and sensitivity (86.3%).

Patients who screened positive for ALVD using the AI model were found to be four times more likely to develop future ventricular dysfunction, highlighting the potential of AI-enhanced ECG as a proactive screening tool for early intervention.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. Attia, ZI., Kapa, S., Lopez-Jimenez, F., et al.[2022]

The AI-ECG algorithm demonstrated strong performance in detecting left ventricular systolic dysfunction (LVSD) in an external population of 4277 adults, achieving an area under the receiver operating curve of 0.82, indicating good accuracy.

While the AI-ECG showed high specificity (97.4%) and accuracy (97.0%), its sensitivity was lower at 26.9%, suggesting that population-specific cut-offs may be needed for optimal clinical use, especially given the differences in patient characteristics compared to the original study.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction. Attia, IZ., Tseng, AS., Benavente, ED., et al.[2021]

AI-enhanced electrocardiograms (AI-ECG) can effectively track changes in cardiac structure and function in patients with obstructive hypertrophic cardiomyopathy (HCM) undergoing treatment with mavacamten, as shown in a study involving 13 patients and 216 ECGs.

Both AI-ECG algorithms demonstrated significant reductions in HCM scores during treatment, correlating well with echocardiographic measures and laboratory markers, suggesting that AI-ECG could be a valuable tool for monitoring therapeutic responses in HCM.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Patient-Level Artificial Intelligence-Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations. Siontis, KC., Abreau, S., Attia, ZI., et al.[2023]

References

1. United States pubmed.ncbi.nlm.nih.gov

A comprehensive artificial intelligence-enabled electrocardiogram interpretation program. [2022]

2. United States pubmed.ncbi.nlm.nih.gov

Screening for cardiac contractile dysfunction using an artificial intelligence-enabled electrocardiogram. [2022]

3. Switzerland pubmed.ncbi.nlm.nih.gov

Current and Future Use of Artificial Intelligence in Electrocardiography. [2023]

4. England pubmed.ncbi.nlm.nih.gov

Clinician Adoption of an Artificial Intelligence Algorithm to Detect Left Ventricular Systolic Dysfunction in Primary Care. [2022]

5. Netherlands pubmed.ncbi.nlm.nih.gov

External validation of a deep learning electrocardiogram algorithm to detect ventricular dysfunction. [2021]

6. United States pubmed.ncbi.nlm.nih.gov

ECG AI-Guided Screening for Low Ejection Fraction (EAGLE): Rationale and design of a pragmatic cluster randomized trial. [2020]

7. Japan pubmed.ncbi.nlm.nih.gov

Deep Learning Models for Predicting Left Heart Abnormalities From Single-Lead Electrocardiogram for the Development of Wearable Devices. [2023]

8. United States pubmed.ncbi.nlm.nih.gov

Detection of Left Atrial Myopathy Using Artificial Intelligence-Enabled Electrocardiography. [2023]

9. United States pubmed.ncbi.nlm.nih.gov

Performance of Off-the-Shelf Machine Learning Architectures and Biases in Detection of Low Left Ventricular Ejection Fraction. [2023]

10. Italy pubmed.ncbi.nlm.nih.gov

[Artificial intelligence applied to the electrocardiogram, or is there really a needle in a haystack?] [2023]

11. United States pubmed.ncbi.nlm.nih.gov

An artificial intelligence-enabled ECG algorithm for comprehensive ECG interpretation: Can it pass the 'Turing test'? [2022]

12. United States pubmed.ncbi.nlm.nih.gov

Patient-Level Artificial Intelligence-Enhanced Electrocardiography in Hypertrophic Cardiomyopathy: Longitudinal Treatment and Clinical Biomarker Correlations. [2023]