Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation

Impacto

Downloads

Downloads per month over past year

Ríos Muñoz, Gonzalo Ricardo and Fernández Avilés, Francisco and Arenal, Ángel (2022) Convolutional Neural Networks for Mechanistic Driver Detection in Atrial Fibrillation. International Journal of Molecular Sciences, 23 (8). p. 4216. ISSN 1422-0067

[thumbnail of ijms-23-04216.pdf]
Preview
PDF
Creative Commons Attribution.

4MB

Official URL: https://doi.org/10.3390/ijms23084216




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.


Item Type:Article
Uncontrolled Keywords:atrial fibrillation; artificial intelligence; rotors; arrhythmias; cardiology; machine learning
Subjects:Medical sciences > Medicine > Cardiology
ID Code:73367
Deposited On:06 Jul 2022 14:49
Last Modified:07 Jul 2022 07:14

Origin of downloads

Repository Staff Only: item control page