English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The heart's contraction is caused by electrical excitation which propagatesthrough the heart muscle. It was recently shown that the electrical excitationcan be computed from the contractile motion of a simulated piece of heartmuscle tissue using deep learning. In cardiac electrophysiology, a primarydiagnostic goal is to identify electrical triggers or drivers of heart rhythmdisorders. However, using electrical mapping techniques, it is currentlyimpossible to map the three-dimensional morphology of the electrical wavesthroughout the entire heart muscle, especially during ventricular arrhythmias.Therefore, the approach to calculate or predict electrical excitation from thehearts motion could be a promising alternative diagnostic approach. Here, wedemonstrate in computer simulations that it is possible to predictthree-dimensional electrical wave dynamics from ventricular deformationmechanics using deep learning. We performed thousands of simulations ofelectromechanical activation dynamics in ventricular geometries and used thedata to train a neural network which subsequently predicts thethree-dimensional electrical wave pattern that caused the deformation. Wedemonstrate that, next to focal wave patterns, even complicatedthree-dimensional electrical wave patterns can be reconstructed, even if thenetwork has never seen the particular arrhythmia. We show that the deeplearning model has the ability to generalize by training it on data generatedwith the smoothed particle hydrodynamics (SPH) method and subsequently applyingit to data generated with the finite element method (FEM). Predictions can beperformed in the presence of scars and with significant heterogeneity. Ourresults suggest that, deep neural networks could be used to calculateintramural action potential wave patterns from imaging data of the motion ofthe heart muscle.

Deep Learning-based Prediction of Electrical Arrhythmia Circuits from Cardiac Motion: An In-Silico Study