AI-Enhanced ECG Interpretation for Structural Heart Disease

(HEART-AI Trial)

Age: 18+

Sex: Any

Trial Phase: Academic

Sponsor: Montreal Heart Institute

Disqualifiers: Arrhythmia, Heart failure, Coronary artery disease, others

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

Compensation: Varies

Number of Visits: Unknown

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial tests an AI-based tool called ECHONEXT, which assists doctors in quickly identifying structural heart disease (SHD) using ECGs (a test that records the heart's electrical activity). The trial aims to determine if the AI's interpretation helps doctors diagnose heart problems more quickly with follow-up tests like heart ultrasounds or MRIs. It compares two groups: one where doctors access the AI's insights and one where they do not. This study is ideal for new patients with heart issues who have not undergone an in-depth heart evaluation or specific heart tests in the past two years. As an unphased trial, it offers patients the chance to contribute to innovative research that could enhance heart disease diagnosis.

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

The trial information does not specify whether participants need to stop taking their current medications.

What prior data suggests that the DeepECG platform is safe for healthcare professionals to use?

Research has shown that the ECHONeXT model for reading ECGs (electrocardiograms) is quite accurate. In previous tests, it was correct in over three-quarters of cases, achieving an accuracy rate of 77.3%. It also demonstrated a sensitivity of 72.6%, successfully detecting many cases of structural heart disease (SHD) when present. The model's specificity was 80.7%, correctly identifying patients without SHD most of the time.

In terms of safety, the ECHONeXT platform poses no health risks because it is a software tool that enhances doctors' ability to read ECGs accurately. It does not involve taking new medicines or undergoing procedures, avoiding the safety concerns associated with drugs or surgeries. This makes the trial a low-risk option for potential participants. ^{1 2 3 4 5}

Why are researchers excited about this trial?

Researchers are excited about ECHONEXT because it enhances ECG interpretation with AI to detect structural heart disease (SHD) more accurately. Unlike traditional methods that rely on manual interpretation and multiple tests, ECHONEXT uses a sophisticated algorithm trained on 800,000 ECG and TTE pairs. This AI-driven approach aims to streamline the diagnostic process, potentially offering quicker and more precise detection of SHD from a single 12-lead ECG. By leveraging AI, ECHONEXT could revolutionize how doctors diagnose SHD, reducing the need for extensive testing and speeding up treatment decisions.

What evidence suggests that the ECHONeXT platform is effective for diagnosing structural heart disease?

Research has shown that the ECHONeXT model, which participants in this trial may experience, can effectively detect structural heart disease (SHD) using just a standard 12-lead ECG test. In a study with 150 ECGs, the model accurately identified SHD in 77.3% of cases. It demonstrated a sensitivity of 72.6% and a specificity of 80.7%, effectively finding SHD and confirming its absence. Additionally, real-world data suggests that the ECHONeXT AI model outperforms skilled heart doctors in spotting hidden SHD. This indicates that the tool could help doctors diagnose SHD more quickly and accurately. ^{1 2 3 5 6}

Are You a Good Fit for This Trial?

This trial is for healthcare professionals at the Montreal Heart Institute who read ECGs, and patients aged 18 or older with single ventricle or structural heart disease. Participants must have recorded a high-quality 12-lead ECG during the study period and given informed consent.

Inclusion Criteria

ECGs of adequate technical quality for interpretation, as determined by the recording software and visual inspection

I visited the outpatient, cardiology clinic, or emergency room for my ECG.

Users providing clinical care and reading ECGs as part of their practice

Exclusion Criteria

Users who are unable to commit to the duration of the study (approximately 1 month minimum) or adhere to the study protocol

ECG with too many artefacts or without any QRS visible as interpreted by the MUSE GE algorithm

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Intervention

Participants in the intervention group receive the ECHONeXT interpretation on 12-lead ECGs to aid in prioritizing transthoracic echocardiography (TTE) and reducing time to diagnosis of structural heart disease.

18 months

Regular visits as per clinical need

Control

Participants in the control group do not receive the ECHONeXT interpretation on 12-lead ECGs.

18 months

Regular visits as per clinical need

Follow-up

Participants are monitored for safety and effectiveness after the intervention period.

4 weeks

What Are the Treatments Tested in This Trial?

Interventions

• ECHONEXT

Trial Overview The HEART-AI trial tests an AI platform called DeepECG that analyzes ECGs to help diagnose structural heart disease faster. It compares time to diagnosis between those using the AI tool (ECHONeXT scores displayed) and standard care without AI assistance.

How Is the Trial Designed?

Group I: ECHONEXT interpretation Experimental Treatment 1 Intervention

The ECHONeXT algorithm was trained to predict the presence of SHD on TTE using a single 12-lead ECG. It was developed at Columbia hospital, released as open-weights and validated at the MHI. It was trained on 800,000 ECG and TTE pairs.

Group II: No ECHONEXT interpretation Active Control 1 Intervention

Not displaying the ECHONEXT algorithm interpretation.

Who Is Running the Clinical Trial?

Montreal Heart Institute

Lead Sponsor

Trials

125

Recruited

85,400+

Published Research Related to This Trial

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]

Citations

1. nature.com nature.com/articles/s41586-025-09227-0

Detecting structural heart disease from electrocardiograms ... In the set of 150 ECGs, the EchoNext model had an accuracy of 77.3%, sensitivity 72.6% and specificity of 80.7%. For the 1,600 non-AI-assisted ...

2. physionet.org physionet.org/content/echonext/

EchoNext: A Dataset for Detecting Echocardiogram- ... This dataset contains a de-identified collection of 100,000 12-lead electrocardiograms (ECGs) with paired structural heart disease (SHD) labels ...

3. clinicaltrials.gov clinicaltrials.gov/study/NCT06462989

Harnessing ECG Artificial Intelligence for Rapid Treatment ... Our primary objective is to assess the impact of displaying the ECHONeXT interpretation on 12-lead ECGs on the time to diagnosis of Structural Heart Disease ( ...

4. reachmd.com reachmd.com/news/real-world-data-shows-echonext-ai-surpasses-cardiologists/2475808/

Real-world Data Shows EchoNext AI Surpasses ... Real-world data on EchoNext AI model efficacy reveals that the tool outperforms skilled cardiologists in detecting hidden structural heart disease.

5. nyp.org nyp.org/advances/article/cardiology/study-shows-ai-screening-tool-developed-at-newyork-presbyterian-and-columbia-can-detect-structural-heart-disease-using-electrocardiogram-data

Study Shows AI Screening Tool Developed at NewYork ... The deep learning model developed by Dr. Pierre Elias and his team accurately identified 77% of structural heart problems, compared with 64% ...

6. reporter.nih.gov reporter.nih.gov/project-details/11029663

Project Details EchoNext is the first successful, unified model detecting all components of SHD from an ECG waveform. The model was built using our database of 12 million ECGs ...