Publications

BibTex format

@unpublished{Martin:2021,
author = {Martin, CH and Oved, A and Chowdhury, RA and Ullmann, E and Peters, NS and Bharath, AA and Varela, M},
publisher = {arXiv},
title = {EP-PINNs: cardiac electrophysiology characterisation using physics-informed neural networks},
url = {http://arxiv.org/abs/2112.07703v1},
year = {2021}
}

Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - Accurately inferring underlying electrophysiological (EP) tissue propertiesfrom action potential recordings is expected to be clinically useful in thediagnosis and treatment of arrhythmias such as atrial fibrillation, but it isnotoriously difficult to perform. We present EP-PINNs (Physics-Informed NeuralNetworks), a novel tool for accurate action potential simulation and EPparameter estimation, from sparse amounts of EP data. We demonstrate, using 1Dand 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporalevolution of action potentials, whilst predicting parameters related to actionpotential duration (APD), excitability and diffusion coefficients. EP-PINNs areadditionally able to identify heterogeneities in EP properties, making thempotentially useful for the detection of fibrosis and other localised pathologylinked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological invitro preparations, by characterising the effect of anti-arrhythmic drugs onAPD using optical mapping data. EP-PINNs are a promising clinical tool for thecharacterisation and potential treatment guidance of arrhythmias.
AU  - Martin,CH
AU  - Oved,A
AU  - Chowdhury,RA
AU  - Ullmann,E
AU  - Peters,NS
AU  - Bharath,AA
AU  - Varela,M
PB  - arXiv
PY  - 2021///
TI  - EP-PINNs: cardiac electrophysiology characterisation using physics-informed neural networks
UR  - http://arxiv.org/abs/2112.07703v1
UR  - http://hdl.handle.net/10044/1/93577
ER  -

Download

DrRashedaChowdhury

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)