VALVE-AI: AI-ECG screening to find moderate or severe heart valve disease.
VALidation of Screening Valvular Heart Disease Using Electrocardiogram Powered by Artificial Intelligence: A Randomized Controlled Trial
NA · National Defense Medical Center, Taiwan · NCT07023510
This project will see if an AI-powered 12-lead ECG can help find moderate or severe valvular heart disease in adults aged 60–85 who get a routine ECG.
Quick facts
| Phase | NA |
|---|---|
| Study type | Interventional |
| Enrollment | 8648 (estimated) |
| Ages | 60 Years to 85 Years |
| Sex | All |
| Sponsor | National Defense Medical Center, Taiwan (other) |
| Locations | 1 site (Taipei) |
| Trial ID | NCT07023510 on ClinicalTrials.gov |
What this trial studies
In this randomized controlled trial, adult outpatients aged 60–85 receiving a standard 12-lead ECG have each ECG analyzed by a validated deep-learning AI that classifies risk for significant valvular heart disease. Participants flagged as high-risk by the AI are randomized to either receive transthoracic echocardiography (experimental arm) or continue usual clinical care without routine echo prompted by the AI result (control arm), while low-risk participants receive routine care. The primary outcome is the rate of newly detected moderate or severe VHD within 90 days post-randomization. Secondary outcomes include time to diagnosis, downstream management changes, and feasibility of integrating AI-ECG screening into outpatient workflows.
Who should consider this trial
Good fit: Adults aged 60–85 who have had a 12-lead ECG within the past year, with no echocardiogram in the prior three years, no known valvular disease, no prior valve surgery, and not post–heart transplant.
Not a fit: People with a recent echocardiogram, known valvular disease, prior valve surgery, post–heart transplant status, or outside the 60–85 age range are unlikely to benefit from this screening approach.
Why it matters
Potential benefit: If successful, AI-guided screening could detect clinically important valve disease earlier, enabling timelier treatment and reducing downstream complications.
How similar studies have performed: AI-ECG methods have shown promise detecting conditions like reduced ejection fraction and atrial fibrillation and some observational work suggests AI can flag valvular disease signals, but randomized trials of AI-ECG screening for VHD are still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * At least one 12-lead ECG within 1 year * Age 60-85 years of age Exclusion Criteria: * Documented echocardiography within 3 years before indexed ECG * Any known valvular heart disease * History of any valvular surgery * Post-heart transplant
Where this trial is running
Taipei
- Tri-Service General Hospital — Taipei, Taiwan (RECRUITING)
Study contacts
- Study coordinator: Chin Lin
- Email: xup6fup0629@gmail.com
- Phone: +886-2-8792-3100
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions: Valvular Heart Disease Patients