Actively Recruiting
AI-Powered ECG Diagnosis and Localization of Tachycardia A Multicenter Registry Study
Led by Inha University Hospital · Updated on 2026-10-30
10000
Participants Needed
1
Research Sites
N/A
Total Duration
AI-Summary
What This Trial Is About
Researchers are evaluating an artificial intelligence AI-powered electrocardiography ECG algorithm to improve the diagnosis and prediction of heart conditions including various types of tachycardia such as paroxysmal supraventricular tachycardia, Wolff-Parkinson-White syndrome, premature ventricular contractions, and ventricular tachycardia. This multicenter retrospective study aims to develop, validate, and apply this AI-ECG technology for better detection of cardiac abnormalities and outcomes prediction. The study uses a deep learning 12-lead ECG algorithm to analyze encrypted raw ECG text data extracted from patients who have undergone electrophysiological studies and radiofrequency catheter ablation. The AI models ability to differentiate tachycardia mechanisms and to localize arrhythmia origin sites will be assessed, using data from these specialized cardiac procedures. Participants are patients aged 19 or older with confirmed tachycardia diagnoses and available ECG text data. Researchers will measure the accuracy of the AI-ECG models by calculating the area under the ROC curve for diagnosing tachycardia types and localizing arrhythmia sites. The study involves reviewing existing medical records and ECG data, with no active treatment administered during the study period, which extends through December 2028.
CONDITIONS
Brief Title
AI-Based Differential Diagnosis and Localization of Tachycardia Using ECG: Multicenter Registry (EP-AI ASSIST)
Research Team
Y
Yongsoo Baek, MD, PhD
Not the Right Trial for You?
Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.
Already have an account? Log in here