Actively Recruiting
Development of an Artificial Intelligence Algorithm to Detect Pathological Repolarization Disorders on the ECG and the Risk of Ventricular Arrhythmias
Led by Assistance Publique - Hôpitaux de Paris · Updated on 2025-07-31
5000
Participants Needed
1
Research Sites
4 weeks
Total Duration
On this page
Sponsors
A
Assistance Publique - Hôpitaux de Paris
Lead Sponsor
U
UMMISCO - Institute of Research for Development (IRD)
Collaborating Sponsor
AI-Summary
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 model's 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.
CONDITIONS
Brief Title
Development of an Artificial Intelligence Algorithm to Detect Pathological Repolarization Disorders on the ECG and the Risk of Ventricular Arrhythmias
Who Can Participate
Eligibility Criteria
You may qualify if you...
- Age 18 years or older
- Patients or subjects receiving care in recruiting centers where an ECG is indicated
- No opposition to participation in the study
You will not qualify if you...
- Medical contraindication for ECG
- Subjects with pacemaker-driven QRS
AI-Screening
AI-Powered Screening
Complete this quick 3-step screening to check your eligibility
Your Study Journey
Duration - 2 to 4 weeks
Participants are screened for eligibility to participate in the trial.
1 visit (in-person)
Duration - Day 0
Participants undergo ECG recordings and clinical data collection to evaluate repolarization disorders using artificial intelligence analysis.
1 visit (in-person) for ECG and data collection
Duration - Up to 42 months
Participants' digital ECGs and clinical data are analyzed to validate the AI model's performance in real-world clinical practice.
No additional visits required; analysis is based on collected data
Trial Site Locations
Total: 1 location
1
Centre d'Investigation Clinique Paris-Est/Hôpital Pitié-Salpêtrière
Paris, France, 75013
Actively Recruiting
Research Team
J
Joe-Elie SALEM, PU-PH
How is the study designed?
Study Type
OBSERVATIONAL
Masking
N/A
Allocation
N/A
Model
N/A
Primary Purpose
N/A
Number of Arms
1
Similar Trials
Frequently Asked Questions
Have more questions? Get in touch with our team for quick support
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