Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation

Abstract

The maintaining and initiating mechanisms of atrial fibrillation (AF) remain controversial. Deep learning is emerging as a powerful tool to better understand AF and improve its treatment, which remains suboptimal. This paper aims to provide a solution to automatically identify rotational activity drivers in endocardial electrograms (EGMs) with convolutional recurrent neural networks (CRNNs). The CRNN model was compared with two other state-of-the-art methods (SimpleCNN and attention-based time-incremental convolutional neural network (ATI-CNN)) for different input signals (unipolar EGMs, bipolar EGMs, and unipolar local activation times), sampling frequencies, and signal lengths. The proposed CRNN obtained a detection score based on the Matthews correlation coefficient of 0.680, an ATI-CNN score of 0.401, and a SimpleCNN score of 0.118, with bipolar EGMs as input signals exhibiting better overall performance. In terms of signal length and sampling frequency, no significant differences were found. The proposed architecture opens the way for new ablation strategies and driver detection methods to better understand the AF problem and its treatment.

Artificial intelligence for atrial fibrillation detection, prediction, and treatment: A systematic review of the last decade (2013–2023)

“…The AI platform was found to be non‐inferior in accuracy for arrhythmia detection but faster compared with the latter. Ríos‐Muñoz et al (2022) used a CNN‐based approach to detect AF starting from endocardial electrograms (EGMs).…”

Review of Ex Vivo Cardiac Electrical Mapping and Intelligent Labeling of Atrial Fibrillation Substrates

“…for re-entrant driver detection. Ríos-Muñoz et al [56] automatically identified rotors in an endocardial electrogram (EGM) using a CRNN with an accuracy of 80.04%. Liao et al [57] applied a deep learning model to an original EGM signal and detected the focal source as a potential ablation target with sensitivity, specificity, and accuracy values of 90%, 81.9%, and 82.5%, respectively.…”

Cardiovascular Diseases in the Digital Health Era: A Translational Approach from the Lab to the Clinic

“…Recently, AI has presented a major impact in the medical sciences [ 68 ] by automatizing tasks and predicting outcomes with unprecedented performance in real-time applications [ 69 , 70 , 71 ]. These advances are occurring at a fast pace in research laboratories that implement algorithms that need to learn or to be trained to achieve high accuracy performance.…”