Latent Representations of Intracardiac Electrograms for Atrial Fibrillation Driver Detection

TL;DR

This paper introduces a deep learning approach using convolutional autoencoders to extract meaningful features from intracardiac electrograms, aiding in the detection of atrial fibrillation drivers during ablation procedures.

Contribution

It presents a novel unsupervised learning framework that characterizes intracardiac signals and improves detection of AF drivers, integrating into clinical mapping systems.

Findings

Autoencoders learned low-loss latent representations preserving EGM morphology.

Moderate detection performance for rotational and focal activity (AUC 0.73-0.76).

High accuracy in identifying atrial EGM entanglement (AUC 0.93).

Abstract

Atrial Fibrillation (AF) is the most prevalent sustained arrhythmia, yet current ablation therapies, including pulmonary vein isolation, are frequently ineffective in persistent AF due to the involvement of non-pulmonary vein drivers. This study proposes a deep learning framework using convolutional autoencoders for unsupervised feature extraction from unipolar and bipolar intracavitary electrograms (EGMs) recorded during AF in ablation studies. These latent representations of atrial electrical activity enable the characterization and automation of EGM analysis, facilitating the detection of AF drivers. The database consisted of 11,404 acquisitions recorded from 291 patients, containing 228,080 unipolar EGMs and 171,060 bipolar EGMs. The autoencoders successfully learned latent representations with low reconstruction loss, preserving the morphological features. The extracted embeddings allowed downstream classifiers to detect rotational and focal activity with moderate performance (AUC 0.73-0.76) and achieved high discriminative performance in identifying atrial EGM entanglement (AUC 0.93). The proposed method can operate in real-time and enables integration into clinical electroanatomical mapping systems to assist in identifying arrhythmogenic regions during ablation procedures. This work highlights the potential of unsupervised learning to uncover physiologically meaningful features from intracardiac signals.