Whole-heart electromechanical simulations using Latent Neural Ordinary Differential Equations
Year: 2024
Type: article
Abstract: Cardiac digital twins provide a physics and physiology informed framework to deliver personalized medicine. However, high-fidelity multi-scale cardiac models remain a barrier to adoption due to their extensive computational costs. Artificial Intelligence-based methods can make the creation of fast and accurate whole-heart digital twins feasible. We use Latent Neural Ordinary Differential Equations (LNODEs) to learn the pressure-volume dynamics of a heart failure patient. Our surrogate model is trained from 400 simulations while accounting for 43 parameters describing cell-to-organ cardiac electromechanics and cardiovascular hemodynamics. LNODEs provide a compact representation of the 3D-0D model in a latent space by means of an Artificial Neural Network that retains only 3 hidden layers with 13 neurons per layer and allows for numerical simulations of cardiac function on a single processor. We employ LNODEs to perform global sensitivity analysis and parameter estimation with uncertainty quantification in 3 hours of computations, still on a single processor.
Source: npj Digital Medicine
Language: English
Subfield: Statistical and Nonlinear Physics
Field: Physics and Astronomy
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,790
Funders: Istituto Nazionale di Alta Matematica "Francesco Severi", Alan Turing Institute, British Heart Foundation, Ministero dell’Istruzione, dell’Università e della Ricerca, National Institutes of Health, Gruppo Nazionale per il Calcolo Scientifico, Engineering and Physical Sciences Research Council, National Heart, Lung, and Blood Institute, H2020 European Research Council, NextGenerationEU
Awards: G1234657840, G1251496372, Predicting Outcome of Rate or Rhythm Control in Patients with Atrial Fibrillation and Heart Failure, G1993080211, Uncertainty Quantification in Prospective and Predictive Patient Specific Cardiac Models, G375838716, G3802727246, G4022907568, G4598076761, G5147728456, G534424066, G5513623408, G6068599298, G6311427306, G6951127647, Modeling the heart across the scales: from cardiac cells to the whole organ, Selecting rhythm or rate control in patients with both atrial fibrillation and heart failure, Scaling Cardiac Biomechanics Digital Twins for Personalised Medicine, Using Atrial Mechanics To Identify Fibrosis In Patients with Atrial Fibrillation, The Alan Turing Institute 22/23 - Core and Additional Funding
OpenAlex ID: W4394722845