Researchoperator learningcardiac electrophysiologysurrogate models
Operator Learning Predicts Cardiac Activation And Repolarization
9.2
Ziarelli et al. (published January 27, 2026) apply Fourier Neural Operators (FNO) and Kernel Operator Learning (KOL) to map applied electrical stimuli to cardiac activation and repolarization times. They evaluate models on synthetic 2D and 3D domains and a realistic left-ventricle geometry, reporting high accuracy and orders-of-magnitude speedups versus Monodomain solvers, enabling fast surrogate simulations for clinical use.
Key Points
- 1Learns mapping from applied stimulus to activation and repolarization time distributions using FNO and KOL
- 2Provides efficient surrogate to computationally expensive Monodomain/Bidomain solvers, enabling orders-of-magnitude speedups
- 3Enables rapid, clinically tractable cardiac simulations on realistic left-ventricle meshes with reduced compute
Scoring Rationale
High novelty and strong usability from peer-reviewed methods; scope limited to simulated cases and a single left-ventricle geometry.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
