A Deep-Learning-Enabled Electrocardiogram for Detecting Pulmonary Hypertension (ADDPH)

National Defense Medical Center, Taiwan

Status: Enrolling

Conditions: Hypertension, Pulmonary; Artificial Intelligence (AI) in Diagnosis; Artificial Intelligence (AI)

Treatments: Diagnostic Test: AI-ECG Guidance

Study type: Interventional

Funder types: Other

Identifiers

NCT07079592

AI-PH

Details and patient eligibility

About

This study aims to validate the use of an artificial intelligence-enabled electrocardiogram (AI-ECG) to screen for elevated PAP. We hypothesize that the AI-ECG model can early identify patients with pulmonary hypertension in high-risk patients, prompting further evaluation through echocardiography, potentially resulting in improving cardiovascular outcomes.

Full description

Pulmonary hypertension is often underdiagnosed due to extensive category of etiology. The diagnosis and treatment of pulmonary hypertension have changed dramatically through the re-defined diagnostic criteria and advanced drug development in the past decade. The application of Artificial Intelligence for the detection of elevated pulmonary arterial pressure (ePAP) was reported recently. An AI model based on electrocardiograms (ECG) has shown promise in not only detecting ePAP but also in predicting future risks related to cardiovascular mortality.

Enrollment: 8,666 estimated patients

Sex: All

Ages: 50 to 85 years old

Volunteers: No Healthy Volunteers

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
• No echocardiography in 3 months before index ECG

Trial design

Primary purpose: Diagnostic

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: None (Open label)

---

8,666 participants in 2 patient groups

AI-ECG guidance

Experimental group

Description:

Participants in this arm undergo screening using the AI-ECG system. Those identified as high-risk for pulmonary hypertension receive echocardiography to confirm the diagnosis and guide subsequent management.

Treatment:

Diagnostic Test: AI-ECG Guidance

Standard clinical care

No Intervention group

Description:

Participants in this arm are screened using the AI-ECG system, but diagnosis and management follow the usual clinical practice without echocardiography.