Cargando…

Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing

The electrical signals triggering the heart's contraction are governed by non-linear processes that can produce complex irregular activity, especially during or preceding the onset of cardiac arrhythmias. Forecasts of cardiac voltage time series in such conditions could allow new opportunities...

Descripción completa

Detalles Bibliográficos
Autores principales: Shahi, Shahrokh, Marcotte, Christopher D., Herndon, Conner J., Fenton, Flavio H., Shiferaw, Yohannes, Cherry, Elizabeth M.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8502981/
https://www.ncbi.nlm.nih.gov/pubmed/34646159
http://dx.doi.org/10.3389/fphys.2021.734178
_version_ 1784581011341836288
author Shahi, Shahrokh
Marcotte, Christopher D.
Herndon, Conner J.
Fenton, Flavio H.
Shiferaw, Yohannes
Cherry, Elizabeth M.
author_facet Shahi, Shahrokh
Marcotte, Christopher D.
Herndon, Conner J.
Fenton, Flavio H.
Shiferaw, Yohannes
Cherry, Elizabeth M.
author_sort Shahi, Shahrokh
collection PubMed
description The electrical signals triggering the heart's contraction are governed by non-linear processes that can produce complex irregular activity, especially during or preceding the onset of cardiac arrhythmias. Forecasts of cardiac voltage time series in such conditions could allow new opportunities for intervention and control but would require efficient computation of highly accurate predictions. Although machine-learning (ML) approaches hold promise for delivering such results, non-linear time-series forecasting poses significant challenges. In this manuscript, we study the performance of two recurrent neural network (RNN) approaches along with echo state networks (ESNs) from the reservoir computing (RC) paradigm in predicting cardiac voltage data in terms of accuracy, efficiency, and robustness. We show that these ML time-series prediction methods can forecast synthetic and experimental cardiac action potentials for at least 15–20 beats with a high degree of accuracy, with ESNs typically two orders of magnitude faster than RNN approaches for the same network size.
format Online
Article
Text
id pubmed-8502981
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher Frontiers Media S.A.
record_format MEDLINE/PubMed
spelling pubmed-85029812021-10-12 Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing Shahi, Shahrokh Marcotte, Christopher D. Herndon, Conner J. Fenton, Flavio H. Shiferaw, Yohannes Cherry, Elizabeth M. Front Physiol Physiology The electrical signals triggering the heart's contraction are governed by non-linear processes that can produce complex irregular activity, especially during or preceding the onset of cardiac arrhythmias. Forecasts of cardiac voltage time series in such conditions could allow new opportunities for intervention and control but would require efficient computation of highly accurate predictions. Although machine-learning (ML) approaches hold promise for delivering such results, non-linear time-series forecasting poses significant challenges. In this manuscript, we study the performance of two recurrent neural network (RNN) approaches along with echo state networks (ESNs) from the reservoir computing (RC) paradigm in predicting cardiac voltage data in terms of accuracy, efficiency, and robustness. We show that these ML time-series prediction methods can forecast synthetic and experimental cardiac action potentials for at least 15–20 beats with a high degree of accuracy, with ESNs typically two orders of magnitude faster than RNN approaches for the same network size. Frontiers Media S.A. 2021-09-27 /pmc/articles/PMC8502981/ /pubmed/34646159 http://dx.doi.org/10.3389/fphys.2021.734178 Text en Copyright © 2021 Shahi, Marcotte, Herndon, Fenton, Shiferaw and Cherry. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
spellingShingle Physiology
Shahi, Shahrokh
Marcotte, Christopher D.
Herndon, Conner J.
Fenton, Flavio H.
Shiferaw, Yohannes
Cherry, Elizabeth M.
Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title_full Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title_fullStr Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title_full_unstemmed Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title_short Long-Time Prediction of Arrhythmic Cardiac Action Potentials Using Recurrent Neural Networks and Reservoir Computing
title_sort long-time prediction of arrhythmic cardiac action potentials using recurrent neural networks and reservoir computing
topic Physiology
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8502981/
https://www.ncbi.nlm.nih.gov/pubmed/34646159
http://dx.doi.org/10.3389/fphys.2021.734178
work_keys_str_mv AT shahishahrokh longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing
AT marcottechristopherd longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing
AT herndonconnerj longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing
AT fentonflavioh longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing
AT shiferawyohannes longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing
AT cherryelizabethm longtimepredictionofarrhythmiccardiacactionpotentialsusingrecurrentneuralnetworksandreservoircomputing