Abstract
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.
Highlights
Cardiac arrhythmias are extremely common pathologies caused by disturbances in the generation or propagation of electrical signals across the heart
We found that EP-Physics Informed Neural Networks (PINNs) could accurately simulate APs even in the absence of ground truth (GT) values for the latent variable W
We found that EP-PINNs could solve the model accurately in the presence of even small numbers of VGT points for training, with root mean squared error (RMSE) ≤ 2.5 × 10−2 even when trained with only 100 points (Figure 3A)
Summary
Cardiac arrhythmias are extremely common pathologies caused by disturbances in the generation or propagation of electrical signals across the heart. Information about cardiac activity can be acquired by recording electrical potentials using electrodes placed on the chest (electrocardiogram, ECG) or, in a catheter lab, placed in direct contact with the myocardium (contact electrograms, EGMs) Expert analysis of these signals is extremely successful in the clinical diagnosis of EP-PINNs arrhythmias and other types of cardiovascular disease [1]. Biophysical models of cardiac electrophysiology [5] are an important tool to understand how cardiac tissue properties affect the generation and propagation of cardiac electrical signals (action potentials, APs) They offer an ideal means for the training and development of computational tools that may aim to infer EP properties from electrical and optical mapping measurements, such as EP-PINNs. Several biophysical EP models have been proposed (see models.cellml.org/electrophysiology), each with varying degrees of detail aiming to reproduce different EP features, cardiac regions or animal/human experimental findings.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
