AI-Enhanced ECG Screening for Cardiomyopathy

Overseen By Brendan Mark

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Mayo Clinic

Disqualifiers: Ischemic heart disease, Valvular abnormality, Congenital heart disease, Hypertension, others

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

Approved in 1 Jurisdiction This treatment is already approved in other countries

Compensation: Varies

Number of Visits: 1

250 Participants Needed

Trial Summary

What is the purpose of this trial?

The purpose of this study is to assess the feasibility and impact of screening FDR of DCM probands using a mobile ECG with the ability to transmit the ECG for cloud-based AI analysis to detect reduced left ventricular ejection fraction (LVEF). This protocol will examine the impact of incorporating the screening AI enhanced ECG into standard of care recommendations.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It's best to discuss this with the trial coordinators or your doctor.

What data supports the effectiveness of the treatment KardiaRx ECG Screening for cardiomyopathy?

Research shows that using artificial intelligence with ECGs (a test that records the heart's electrical activity) can effectively detect heart problems like left ventricular systolic dysfunction, which is related to cardiomyopathy. This AI-enhanced method has been shown to be accurate and useful in identifying heart issues early, even in people without symptoms, making it a promising tool for screening. ^{1 2 3 4 5}

Is AI-Enhanced ECG Screening for Cardiomyopathy safe for humans?

The research does not provide specific safety data for AI-Enhanced ECG Screening for Cardiomyopathy, but it discusses the use of mobile ECG devices and computer-assisted ECG interpretation, which are generally used to improve diagnostic accuracy and patient management without indicating any significant safety concerns. ^{6 7 8 9 10}

How does the AI-Enhanced ECG Screening for Cardiomyopathy treatment differ from other treatments?

This treatment is unique because it uses artificial intelligence to analyze ECGs (electrocardiograms) to detect cardiomyopathy, a heart condition, early and non-invasively. Unlike traditional methods, this AI-enhanced approach can identify heart issues before symptoms appear, potentially improving early intervention and management. ^{2 3 4 11 12}

Research Team

Naveen Pereira, M.D.

Principal Investigator

Mayo Clinic

Eligibility Criteria

This trial is for first-degree relatives (FDR) of individuals with dilated cardiomyopathy (DCM), aiming to detect early heart function issues using a mobile ECG device. Participants should be willing to use the device and transmit data for analysis.

Inclusion Criteria

FDR: Proband has provided informed consent

FDR: Able to provide informed consent

I have been diagnosed with dilated cardiomyopathy and my heart's pumping efficiency is 45% or less.

Exclusion Criteria

My heart condition is not caused by other known heart issues.

My heart muscle disease was caused by a sudden or reversible condition.

I have told my close relatives to get heart screenings.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

AI-ECG Screening

Participants undergo AI-enhanced ECG screening to detect reduced left ventricular ejection fraction

Baseline

1 visit (virtual)

Follow-up

Participants are monitored for safety and effectiveness after AI-ECG screening

4 weeks

Treatment Details

Interventions

• KardiaRx ECG Screening

Trial Overview The study tests the KardiaRx ECG Screening's effectiveness in identifying reduced left ventricular ejection fraction, an indicator of potential heart problems, compared to standard care which includes screening with an echocardiogram.

Participant Groups

Group I: First degree relatives Experimental Treatment 1 Intervention

Subjects who are first-degree relatives of patients with DCM

Group II: DCM (Dilated Cardiomyopathy) Patients Experimental Treatment 1 Intervention

Subjects who are diagnosed with DCM (dilated cardiomyopathy).

Who Is Running the Clinical Trial?

Mayo Clinic

Lead Sponsor

Trials

3,427

Recruited

3,221,000+

Findings from Research

A study involving 221,846 ECGs from four institutions aimed to develop AI models for detecting left ventricular systolic dysfunction (LVSD) with an ejection fraction (EF) <40%, showing promising internal accuracy but variable external validation results.

The performance of AI models varied significantly between institutions, emphasizing the need for external validation and careful consideration of patient characteristics and ECG abnormalities when using AI for LVSD detection.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Importance of external validation and subgroup analysis of artificial intelligence in the detection of low ejection fraction from electrocardiograms. Yagi, R., Goto, S., Katsumata, Y., et al.[2023]

Artificial intelligence-enabled electrocardiography (AIeECG) shows high diagnostic accuracy for detecting left ventricular systolic dysfunction (LVSD), with a median area under the curve (AUC) of 0.90, sensitivity of 83.3%, and specificity of 87% across various populations.

AIeECG can be particularly beneficial in non-cardiology settings and when used alongside natriuretic peptide testing, but further prospective randomized trials are needed to assess its impact on treatment outcomes and cost-effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Artificial intelligence enabled ECG screening for left ventricular systolic dysfunction: a systematic review. Bjerkén, LV., Rønborg, SN., Jensen, MT., et al.[2023]

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]

An artificial intelligence-augmented ECG (AI-ECG) model can accurately predict left ventricular systolic dysfunction (LVSD) in critical care patients, providing a non-invasive and cost-effective alternative to traditional echocardiography.

The AI-ECG algorithm performs well regardless of the presence of atrial fibrillation (AF), making it a versatile tool for early detection of LVSD, which can improve clinical decision-making in acute care settings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The effect of cardiac rhythm on artificial intelligence-enabled ECG evaluation of left ventricular ejection fraction prediction in cardiac intensive care unit patients. Kashou, AH., Noseworthy, PA., Lopez-Jimenez, F., et al.[2021]

In a study involving 583 patients across 27 cardiology practices, the ZOLL Arrhythmia Monitoring System, which combines ECG data with additional biometric information, led to treatment plan changes in 96% of cases, demonstrating its significant impact on patient management.

The integration of biometric data allowed for modifications in medications, follow-up, and lifestyle changes for 64% of patients, suggesting that this next-generation monitoring system enhances the ability of physicians to assess cardiovascular risks and improve overall patient care.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Next-generation Mobile Cardiac Telemetry: Clinical Value of Combining Electrocardiographic and Physiologic Parameters. Yoo, D., Bhalla, K., Manyam, H., et al.[2022]

Computer-assisted interpretation of ECGs and VCGs significantly enhances diagnostic accuracy compared to traditional visual analysis, addressing limitations of conventional methods.

The optimization of ECG data processing functions, along with ongoing improvements in arrhythmia and pediatric VCG programs, suggests that computerized electrocardiography will lead to more standardized and accurate diagnoses in the future.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Computer-assisted interpretation of electro- and vectorcardiograms. Chapter IV. Achievements in the field of computer-assisted interpretation of electrocardiograms. Brohet, C.[2004]

The Alivecor Kardia Mobile device produces accurate single-lead ECG tracings in pediatric patients, showing strong agreement with standard 12-lead ECGs, making it a reliable tool for monitoring heart rhythms in children.

In a study of 30 pediatric patients, the device demonstrated a specificity of 87% for detecting atrial fibrillation, indicating it can effectively identify abnormal rhythms, although it had some false positives related to other rhythm abnormalities.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Can smartphone wireless ECGs be used to accurately assess ECG intervals in pediatrics? A comparison of mobile health monitoring to standard 12-lead ECG. Gropler, MRF., Dalal, AS., Van Hare, GF., et al.[2019]

In a study of 156 healthy volunteers undergoing 24-hour ambulatory cardiac monitoring, only 13% showed normal sinus rhythm, highlighting a significant prevalence of cardiac abnormalities in this population.

The most common finding was supraventricular ectopics (83%), with other issues like ventricular ectopics and sinus pauses also noted, suggesting the need for clear guidelines to evaluate cardiac health before trials of new drugs.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Use of 24 h ambulatory ECG recordings in the assessment of new chemical entities in healthy volunteers. Stinson, JC., Pears, JS., Williams, AJ., et al.[2020]

In a study of 14 apparently healthy patients with high amplification ECG abnormalities, minor conduction disorders, particularly in the right bundle branch (RBB), were identified as the likely cause, despite normal heart function and no significant cardiac events during follow-up.

The most common ECG finding in these patients was a deep S wave in leads V5-V6, which can help in diagnosing these minor conduction issues after ruling out other heart conditions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

[Possible mechanisms of false positive results of averaged ECG]. Brembilla-Perrot, B., Beurrier, D., Jacquemin, L., et al.[2014]

An artificial intelligence model (AI-ECG) demonstrated high accuracy in detecting hypertrophic cardiomyopathy (HCM) in pediatric patients, achieving a sensitivity of 92% and specificity of 95% based on a study of 300 children and adolescents.

The AI-ECG model showed excellent performance across different age groups, with an area under the curve (AUC) of 0.98, indicating its potential as a reliable screening tool for HCM using standard 12-lead ECGs.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Detection of hypertrophic cardiomyopathy by an artificial intelligence electrocardiogram in children and adolescents. Siontis, KC., Liu, K., Bos, JM., 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. England pubmed.ncbi.nlm.nih.gov

Importance of external validation and subgroup analysis of artificial intelligence in the detection of low ejection fraction from electrocardiograms. [2023]

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

Artificial intelligence enabled ECG screening for left ventricular systolic dysfunction: a systematic review. [2023]

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

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

4. Netherlands pubmed.ncbi.nlm.nih.gov

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

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

The effect of cardiac rhythm on artificial intelligence-enabled ECG evaluation of left ventricular ejection fraction prediction in cardiac intensive care unit patients. [2021]

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

Next-generation Mobile Cardiac Telemetry: Clinical Value of Combining Electrocardiographic and Physiologic Parameters. [2022]

7. Belgium pubmed.ncbi.nlm.nih.gov

Computer-assisted interpretation of electro- and vectorcardiograms. Chapter IV. Achievements in the field of computer-assisted interpretation of electrocardiograms. [2004]

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

Can smartphone wireless ECGs be used to accurately assess ECG intervals in pediatrics? A comparison of mobile health monitoring to standard 12-lead ECG. [2019]

9. England pubmed.ncbi.nlm.nih.gov

Use of 24 h ambulatory ECG recordings in the assessment of new chemical entities in healthy volunteers. [2020]

10. France pubmed.ncbi.nlm.nih.gov

[Possible mechanisms of false positive results of averaged ECG]. [2014]

11. Netherlands pubmed.ncbi.nlm.nih.gov

Detection of hypertrophic cardiomyopathy by an artificial intelligence electrocardiogram in children and adolescents. [2021]

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

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