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.
The goal of this observational registry is to collect a curated dataset of multimodal imaging data that will serve for development of artificial-intelligence based solutions for prediction of risk and outcomes in patients with atrial fribrillation. Type of study: observational study Study Participants: Patients with atrial fibrillation or atrial flutter who undergo clinically indicated transesophageal echocardiography before catheter ablation or cardioversion. We hypothesize, that automatic analysis of video images of transthoracic echocardiography with deep learning combined with clinical data can predict the presence of left atrial appendage thrombus (LAT). Therefore, our main aim is to create and validate an artificial intelligence model to predict the presence of LAT based on automatic analysis of transthoracic echocardiography with artificial intelligence.
• \- All patients with AF or AFl in whom TEE will be performed (to assess their eligibility for cardioversion or ablation), hospitalized in a participating center during study period (all consecutive patients).