AI-Based Detection of Heart Electrical Disorders and Risk of Dangerous Ventricular Arrhythmias Using ECG Analysis

What this Trial Is About

Researchers are evaluating an artificial intelligence AI model designed to detect pathological repolarization disorders on electrocardiograms ECG and predict the risk of ventricular arrhythmias, specifically Torsades de Pointes TdP related to Long QT LQT syndromes. These conditions can be congenital or drug-induced, affecting cardiac ion channels and prolonging ventricular repolarization, which increases the risk of dangerous arrhythmias. Current screening methods rely mainly on QTc interval measurement and genetic testing, which have limitations in real-world clinical practice. The AI model aims to improve the detection and classification of LQT types and TdP risk by analyzing ECG features beyond QTc alone. This observational study will collect digital ECG data, clinical history, medication use, and genetic information from 5,000 participants across multiple hospitals. The AI model automatically measures ECG parameters such as QTc, PR, QRS duration, and heart rate, and provides probabilistic scores for different congenital and drug-induced LQT types and TdP risk. Data analysis compares AI measurements with reference methods to validate the models performance in real-world conditions. ECGs are anonymized and centrally stored for analysis during this 42-month study. Participants are patients who require an ECG as part of their routine care or research involvement and have no contraindications for ECG. The study measures the agreement between AI and reference QTc measurements and evaluates the accuracy of AI scores for LQT types and TdP risk on the day of ECG recording. The goal is to enhance real-time ECG interpretation and risk classification to improve arrhythmia management, particularly in settings without specialized rhythmology expertise. The total participation involves a single ECG assessment with data collection from clinical and genetic records.

Development of an Artificial Intelligence Algorithm to Detect Pathological Repolarization Disorders on the ECG and the Risk of Ventricular Arrhythmias