AI-powered ECG to help diagnose and predict outcomes in heart disease
Official title: Research for the Development and Clinical Application of Artificial Intelligence-powered Electrocardiography for Diagnosis and Prognostic Prediction in Cardiovascular Disease (AI-CVD): Multicenter Retrospective Study
Run by Inha University Hospital · NCT07856472 · Data updated 2026-11-12
Researchers test an AI-enhanced ECG to help diagnose and predict outcomes for people with cardiovascular diseases.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 10000 (estimated) |
| Sponsor | Inha University Hospital Academic / other |
| Locations | 1 site (Incheon, Incheon) |
| Status | Recruiting |
| Started | March 1, 2023 |
| Main results expected | March 1, 2028 |
| Study ends | March 1, 2028 |
| Registry record updated | October 2, 2026 |
| Trial ID | NCT07856472 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18 years or older with cardiovascular diseases who have accessible 12-lead ECG records suitable for text extraction (XML).
✕Probably not a fit
Patients whose ECG data are incomplete, non-mappable to the XML format, or whose conditions fall outside the study’s target diagnoses may not benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This multicenter retrospective analysis uses encrypted 12-lead ECG data and deep neural networks to develop and validate an AI-ECG algorithm for diagnosing coronary artery disease, heart failure, and related conditions, then assesses how well it predicts patient outcomes in real-world cohorts from 2005 to 2022. The study combines Bi-LSTM and attention-based modeling to extract meaningful patterns from ECG text data (XML) while ensuring privacy through data encryption. It aims to demonstrate clinical utility of AI-ECG in supporting decision-making across tertiary centers in South Korea. No prospective interventions are performed; analysis is restricted to existing ECG records collected at participating sites. Outcomes will focus on diagnostic accuracy and prognostic performance of the AI-ECG models.
Why it matters
Potential benefit: If successful, the AI-ECG tool could improve early detection and risk stratification of cardiovascular diseases using widely available ECG data.
How similar studies have gone: Previous studies have shown promise for AI-ECG approaches in diagnosis and prognosis, though this multicenter retrospective design adds breadth and real-world applicability.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Patients aged 18 years or older diagnosed with cardiovascular diseases, including coronary artery disease and heart failure. * Patients with 12-lead electrocardiogram (ECG) records extractable as text (XML Exclusion Criteria: \- Patients deemed inappropriate as study subjects by the investigator's judgment
Where it's running
-
Inha University Hospital
Incheon, Incheon, South Korea Recruiting
Study contacts
- Study coordinator: Yongsoo Baek, MD, PhD
- Email: existsoo@inha.ac.kr
- Phone: +82-32-890-2200
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Observing clinical outcomes in patients with cardiovascular diseases
This study looks at how people with heart diseases, like coronary heart disease and heart failure, do over time to see what factors affect their health and risk of serious events.
-
Using advanced cardiac imaging to improve treatment for patients with chest pain
This study is testing if using advanced heart imaging techniques can help people with chest pain get better treatment and feel healthier compared to standard care.
-
Pace-and-ablate strategy in atrial fibrillation: who benefits and long-term outcomes
This study looks at adults with atrial fibrillation who underwent AV node ablation with permanent pacing to see who develops pacing-induced problems and how they do long-term.
-
AI-based cardiac analysis using 12-lead and 1-lead ECG
A clinician-facing pilot test to see if SmartECG-EF helps evaluate heart function using both 12-lead and single-lead ECGs in adults with heart conditions.
-
Photoplethysmography-based algorithm to detect atrial fibrillation in heart failure patients
A wearable-based, AI-powered test using PPG signals to see if a patient with heart failure has atrial fibrillation.
-
Intrahospital flu vaccine for adults with high cardiovascular risk when admitted for ACS or heart failure
This study tests whether offering a flu vaccine at the bedside during a hospital stay, along with counseling, increases vaccination rates for adults with acute coronary syndrome or heart failure who are at high cardiovascular risk.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.