Artificial Intelligence in Cardiac Electrophysiology: A Comprehensive Review
Pietro Cipollone, Nicola Pierucci, Andrea Matteucci, Massimiliano Palombi, Domenico Laviola, Raffaele Bruti, Sara Vinciullo, Marco Bernardi, Luigi Spadafora, Angelica Cersosimo, Sara Trivigno, Tommaso Recchioni, Agostino Piro, Cristina Chimenti, Claudio Pandozi, Carmine Dario Vizza, Carlo Lavalle, Marco Valerio Mariani
Abstract
Background: Artificial Intelligence (AI) is a transformative innovation designed to enable machines to perform tasks typically requiring human intelligence. Among various medical fields, cardiology—and particularly electrophysiology—has seen rapid integration of AI technologies. The ability of AI to analyze large and complex datasets is reshaping diagnostic and therapeutic approaches. Objectives: This review aims to provide a comprehensive overview of AI models and their applications in cardiac electrophysiology. The focus is on understanding how AI contributes to clinical practice through ECG interpretation, arrhythmia detection, atrial mapping, and catheter ablation, while also exploring its limitations and future potential. Methods: The review discusses various AI approaches, including Machine Learning (ML) and Deep Learning (DL), and highlights relevant literature illustrating their implementation in electrophysiological settings. Key clinical applications are examined thematically, with a narrative synthesis of current capabilities, technologies, and outcomes. Results: AI-based tools have demonstrated effectiveness in identifying supraventricular arrhythmias like atrial fibrillation (AF) and atrial flutter (AFL), as well as complex conditions such as ventricular tachycardias (VTs) and long QT syndrome (LQTS). In procedural contexts, AI enhances electro-anatomical mapping, reduces operative time, and supports tailored post-ablation management. Discussion: While AI offers clear advantages in diagnostic accuracy and procedural efficiency, challenges remain regarding data security, ethical transparency, and clinical adoption. Addressing these limitations will be crucial for integrating AI into routine electrophysiology and maximizing its potential in future cardiology practice.