Identification of Ablation Sites in Persistent Atrial Fibrillation Based on Spatiotemporal Dispersion of Electrograms Using Machine Learning

Abstract

A recent patient-tailored ablation protocol to treat atrial fibrillation consists in identifying ablation sites based on their spatiotemporal dispersion (STD). STD represents a delay of the cardiac activation observed in intracardiac electrograms (EGMs) across contiguous leads. This work aims at automatically identifying ablation sites by classifying EGM data acquired by the PentaRay catheter into ablated vs. non-ablated groups using machine learning. More than 35000 multichannel recordings are acquired from 15 persistent AF patients. An annotation model is designed to label the dataset. The classifiers include: (1) multivariate logistic regression; (2) LeNet-STD, a shallow convolutional neural network. A binary label identifying whether the mapped site contains STD pattern according to the interventional cardiologist is combined to raw EGMs as classifiers input. The LeNet-STD combined with data augmentation yields the best performance with an F1-score of 76%.