Multimodal, Multicentre Registry of Clinical and Imaging Data to Develop Predictive Models Based on Artificial Intelligence to Support the Diagnostic and Therapeutic Process for Patients with Atrial Fibrillation Undergoing Catheter Ablation and Cardioversion

What this Trial Is About

Researchers are collecting detailed imaging and clinical data from patients with atrial fibrillation or atrial flutter who undergo transesophageal echocardiography to better understand and predict the risks associated with left atrial appendage thrombus (LAT). This observational study aims to develop artificial intelligence models that analyze transthoracic echocardiography images and clinical information to predict the presence of LAT, which is linked to stroke risk and complicates cardioversion or catheter ablation procedures. The study involves gathering multimodal imaging data including transesophageal echocardiography, transthoracic echocardiography, cardiac CT, cardiac magnetic resonance, and electrocardiograms, both retrospectively and prospectively. Patients undergo clinically indicated transesophageal echocardiography before catheter ablation or cardioversion. Optional imaging modalities and clinical data are collected to form a comprehensive database that supports AI-based model development and validation. Participants will have their imaging data and clinical records collected during hospitalization, with follow-up data on adverse outcomes and atrial fibrillation recurrence tracked for up to one year. Researchers will assess the presence of left atrial appendage thrombus using these data, aiming to improve diagnostic and therapeutic approaches. The study involves no treatment administration but focuses on detailed imaging acquisition and clinical monitoring to support artificial intelligence research.

Multimodal Cardiac Imaging Registry in Patients with Atrial Fibrillation