Deep-learning ECG to detect pulmonary hypertension
A Deep-Learning-Enabled Electrocardiogram for Detecting Pulmonary Hypertension: A Randomized Controlled Trial
This trial tests whether an AI-powered ECG can spot high blood pressure in the lungs (pulmonary hypertension) in adults aged 50–85 who have had a recent ECG.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 8666 (estimated) |
| Ages | 50 Years to 85 Years |
| Sex | All |
| Sponsor | National Defense Medical Center, Taiwan Academic / other |
| Locations | 1 site (Taipei) |
| Trial ID | NCT07079592 on ClinicalTrials.gov |
What this trial studies
This interventional study applies a deep-learning algorithm to routine 12-lead ECGs to screen for elevated pulmonary arterial pressure in older adults. Participants aged 50–85 with a 12-lead ECG within the prior three months will have the AI-ECG analyzed to identify likely elevated PAP. Those flagged by the algorithm would be prompted to undergo echocardiography for confirmation and potential clinical follow-up. The protocol excludes patients with known pulmonary hypertension, certain cardiomyopathies, prior heart or lung transplants, or very high prior echocardiographic pressures to focus on undiagnosed or high-risk cases.
Who should consider this trial
Good fit: Ideal candidates are adults 50–85 years old who have had at least one 12‑lead ECG within the last three months and do not have a prior diagnosis of pulmonary hypertension, excluded cardiomyopathies, or prior heart/lung transplants.
Not a fit: Patients with an existing diagnosis of pulmonary hypertension, certain cardiomyopathies, prior heart or lung transplants, very high previously measured pulmonary pressures, or without a recent ECG are unlikely to benefit from this screening approach.
Why it matters
Potential benefit: If successful, this approach could enable earlier, noninvasive detection of pulmonary hypertension and lead to faster diagnostic workups and potentially better outcomes.
How similar studies have performed: Earlier reports have shown promising results for AI-ECG algorithms in detecting elevated pulmonary arterial pressure and predicting cardiovascular outcomes, but broader validation is still limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Men or women, ≥ 50 to 85 years of age * At least one 12-lead ECG within 3 months Exclusion Criteria: * A diagnosis of PH WHO Groups 1, 2, 3, 4, or 5 * A diagnosis of hypertrophic cardiomyopathy, restrictive cardiomyopathy, constrictive pericarditis, cardiac amyloidosis, or infiltrative cardiomyopathy * Prior heart, lung, or heart-lung transplants * Any systolic pulmonary artery pressure \>50 mmHg by echocardiography before * Echocardiography in 3 months before index ECG
Where this trial is running
Taipei
- National Defense Medical Center — Taipei, Taiwan (Recruiting)
Study contacts
- Study coordinator: Chin Lin, Associate Professor
- Email: up6fup0629@gmail.com
- Phone: 886+2-87923311
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.