EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks
Accurately inferring underlying electrophysiological (EP) tissue properties from action potential recordings is expected to be clinically useful in the diagnosis and treatment of arrhythmias such as atrial fibrillation. It is, however, notoriously difficult to perform. We present EP-PINNs (Physics I...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-02-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2021.768419/full |
| _version_ | 1798022530576941056 |
|---|---|
| author | Clara Herrero Martin Clara Herrero Martin Alon Oved Rasheda A. Chowdhury Elisabeth Ullmann Nicholas S. Peters Anil A. Bharath Marta Varela |
| author_facet | Clara Herrero Martin Clara Herrero Martin Alon Oved Rasheda A. Chowdhury Elisabeth Ullmann Nicholas S. Peters Anil A. Bharath Marta Varela |
| author_sort | Clara Herrero Martin |
| collection | DOAJ |
| description | Accurately inferring underlying electrophysiological (EP) tissue properties from action potential recordings is expected to be clinically useful in the diagnosis and treatment of arrhythmias such as atrial fibrillation. It is, however, notoriously difficult to perform. We present EP-PINNs (Physics Informed Neural Networks), a novel tool for accurate action potential simulation and EP parameter estimation from sparse amounts of EP data. We demonstrate, using 1D and 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporal evolution of action potentials, whilst predicting parameters related to action potential duration (APD), excitability and diffusion coefficients. EP-PINNs are additionally able to identify heterogeneities in EP properties, making them potentially useful for the detection of fibrosis and other localised pathology linked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological in vitro preparations, by characterising the effect of anti-arrhythmic drugs on APD using optical mapping data. EP-PINNs are a promising clinical tool for the characterisation and potential treatment guidance of arrhythmias. |
| first_indexed | 2024-04-11T17:31:28Z |
| format | Article |
| id | doaj.art-b8a108f341ba4a9fb84e9f0c29121243 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-04-11T17:31:28Z |
| publishDate | 2022-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-b8a108f341ba4a9fb84e9f0c291212432022-12-22T04:11:59ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2022-02-01810.3389/fcvm.2021.768419768419EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural NetworksClara Herrero Martin0Clara Herrero Martin1Alon Oved2Rasheda A. Chowdhury3Elisabeth Ullmann4Nicholas S. Peters5Anil A. Bharath6Marta Varela7Department of Bioengineering, Imperial College London, London, United KingdomITACA Institute, Universitat Politècnica de València, Valencia, SpainDepartment of Computing, Imperial College London, London, United KingdomNational Heart and Lung Institute, Imperial College London, London, United KingdomDepartment of Mathematics, Technical University of Munich, Munich, GermanyNational Heart and Lung Institute, Imperial College London, London, United KingdomDepartment of Bioengineering, Imperial College London, London, United KingdomNational Heart and Lung Institute, Imperial College London, London, United KingdomAccurately inferring underlying electrophysiological (EP) tissue properties from action potential recordings is expected to be clinically useful in the diagnosis and treatment of arrhythmias such as atrial fibrillation. It is, however, notoriously difficult to perform. We present EP-PINNs (Physics Informed Neural Networks), a novel tool for accurate action potential simulation and EP parameter estimation from sparse amounts of EP data. We demonstrate, using 1D and 2D in silico data, how EP-PINNs are able to reconstruct the spatio-temporal evolution of action potentials, whilst predicting parameters related to action potential duration (APD), excitability and diffusion coefficients. EP-PINNs are additionally able to identify heterogeneities in EP properties, making them potentially useful for the detection of fibrosis and other localised pathology linked to arrhythmias. Finally, we show EP-PINNs effectiveness on biological in vitro preparations, by characterising the effect of anti-arrhythmic drugs on APD using optical mapping data. EP-PINNs are a promising clinical tool for the characterisation and potential treatment guidance of arrhythmias.https://www.frontiersin.org/articles/10.3389/fcvm.2021.768419/fullcardiac electrophysiologyarrhythmia (any)Physics Informed Neural Network (PINN)atrial fibrillationparameter estimationoptical mapping |
| spellingShingle | Clara Herrero Martin Clara Herrero Martin Alon Oved Rasheda A. Chowdhury Elisabeth Ullmann Nicholas S. Peters Anil A. Bharath Marta Varela EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks Frontiers in Cardiovascular Medicine cardiac electrophysiology arrhythmia (any) Physics Informed Neural Network (PINN) atrial fibrillation parameter estimation optical mapping |
| title | EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks |
| title_full | EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks |
| title_fullStr | EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks |
| title_full_unstemmed | EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks |
| title_short | EP-PINNs: Cardiac Electrophysiology Characterisation Using Physics-Informed Neural Networks |
| title_sort | ep pinns cardiac electrophysiology characterisation using physics informed neural networks |
| topic | cardiac electrophysiology arrhythmia (any) Physics Informed Neural Network (PINN) atrial fibrillation parameter estimation optical mapping |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2021.768419/full |
| work_keys_str_mv | AT claraherreromartin eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT claraherreromartin eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT alonoved eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT rashedaachowdhury eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT elisabethullmann eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT nicholasspeters eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT anilabharath eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks AT martavarela eppinnscardiacelectrophysiologycharacterisationusingphysicsinformedneuralnetworks |