Peak-based spatio-temporal dispersion classifier of multipolar intracardiac electrograms in persistent atrial fibrillation

Description

Atrial fibrillation (AF) is a common cardiac condition that predominantly affects the elderly, posing a significant risk for stroke and raising public health concerns. Catheter ablation (CA) is the most effective long-term treatment for persistent AF. A novel CA approach based on spatio-temporal dispersion (STD) targets active zones that sustain the arrhythmia. STD detection relies on visual interpretation of multipolar electrograms (EGMs). Identifying local activations time shifting among leads is critical for determining the presence of STD. However, current literature advocating for the use of machine learning (ML) for STD classification lacks a thorough methodological analysis, reproducibility and is challenging for cardiologists to interpret. In this study, we present a new peak-based STD classifier using data solely for testing. This mathematical algorithm models the reasoning process of interventional cardiologists during STD-based CA, translating the manual classification process into signal processing operations to enhance explainability and interpretability. Results show that the peak-based classifier improves accuracy over previous methods.

Abstract

International audience

Additional details