Real-time Generalizable Heart Valve Mechanics for Clinical Disease Assessment via a Physics-Conditioned Neural Operator
cs.LG
Submitted: 2026-09-20
Updated: 2026-09-20
Comments: Preprint submission
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: Mitral regurgitation is the most common heart valve disorder worldwide, affecting over 2% of the global population, rising to at least 10% in adults over 75, and causing approximately 15% of valvular
Terminology
Abstract
Mitral regurgitation is the most common heart valve disorder worldwide, affecting over 2% of the global population, rising to at least 10% in adults over 75, and causing approximately 15% of valvular heart disease-related deaths. Yet only a minority of patients with severe disease undergo corrective surgery. Rapid assessment of valve mechanics could enable earlier, more precise intervention, but traditional finite element simulations remain too slow for clinical timelines and parameter sweeps. We introduce the Physics-Conditioned Neural Operator (PCNO), a transformer-based surrogate that predicts leaflet displacement, strain, and stress fields across mitral and tricuspid geometries, conditioned on systolic blood pressure and tissue properties. Trained on functional, regurgitated, and pathological valves, including tethering, P2 prolapse, and annular dilation, PCNO achieves up to a 15,260x speedup over fine mesh finite element simulations with comparable accuracy, identifies pathology class, and resolves diagnostic metrics within 3.5% error under out-of-distribution extrapolation.
Sources
- Simulation of Transcatheter Therapies for Atrioventricular Valve Regurgitation in an Open-Source Finite Element Simulation Framework
- A Foundation Model for the Earth System
- Rethinking Attention with Performers
- Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
- On the "Induction Bias" in Sequence Models
- DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training
- Training Compute-Optimal Large Language Models
- Perceiver IO: A General Architecture for Structured Inputs & Outputs
- FeatureGS: Eigenvalue-Feature Optimization in 3D Gaussian Splatting for Geometrically Accurate and Artifact-Reduced Reconstruction
- Scaling Laws for Neural Language Models
- Adam: A Method for Stochastic Optimization
- Uncertainty Quantification for Machine Learning in Healthcare: A Survey
- Decoupled Weight Decay Regularization
- Multiple Physics Pretraining for Physical Surrogate Models
- Walrus: A Cross-Domain Foundation Model for Continuum Dynamics
- Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits
- When PINNs Go Wrong: Pseudo-Time Stepping Against Spurious Solutions
- CViT: Continuous Vision Transformer for Operator Learning
- Linformer: Self-Attention with Linear Complexity
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks