Graphical Analysis of the Progression of Atrial Arrhythmia Using Recurrent Neural Networks

Authors

Nahuel Costa^1, , Jesús Fernández², Inés Couso^3, , Luciano Sánchez^{1, *,}

¹Computer Science Department, University of Oviedo, Gijón, Asturias, Spain

²Medtronic, S.A. Gijón, Asturias, Spain

³Statistics Department, University of Oviedo, Gijón, Asturias, Spain

^*Corresponding author. Email: luciano@uniovi.es

DOI

10.2991/ijcis.d.200926.001How to use a DOI?

Keywords

Heart disease; Graphical analysis; Generative networks; Recurrent neural networks; Time series

Abstract

Pacemaker logs are used to predict the progression of paroxysmal cardiac arrhythmia to permanent atrial fibrillation by means of different deep learning algorithms. Recurrent Neural Networks are trained on data produced by a generative model. The activations of the different nets are displayed in a graphical map that helps the specialist to gain insight into the cardiac condition. Particular attention was paid to Generative Adversarial Networks (GANs), whose discriminative elements are suited for detecting highly specific sets of arrhythmias. The performance of the map is validated with simulated data with known properties and tested with intracardiac electrograms obtained from pacemakers and defibrillator systems.

Copyright

© 2020 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Nahuel Costa
AU  - Jesús Fernández
AU  - Inés Couso
AU  - Luciano Sánchez
PY  - 2020
DA  - 2020/10/06
TI  - Graphical Analysis of the Progression of Atrial Arrhythmia Using Recurrent Neural Networks
JO  - International Journal of Computational Intelligence Systems
SP  - 1567
EP  - 1577
VL  - 13
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.200926.001
DO  - 10.2991/ijcis.d.200926.001
ID  - Costa2020
ER  -