Abstract

We propose a non-intrusive method, based on Artificial Neural Networks (ANNs), that builds reduced-order models (ROMs) approximating the dynamics of 3D cardiac electromechanics. Our Machine Learning method allows for real-time numerical simulations of the cardiac function, accounting for the dependence on a set of parameters associated with the full-order model (FOM) to be surrogated. The ANN-based ROM is trained from a collection of pressure-volume transients obtained through the FOM and it can then be coupled with hemodynamic models for the blood circulation external to the heart, in the same manner as the original electromechanical model, but at a dramatically lower computational cost. We demonstrate the effectiveness of the proposed method in two relevant contexts in cardiac modeling. First, we employ the ANN-based ROM to perform a global sensitivity analysis on both the electromechanical and hemodynamic models. Second, we perform a Bayesian estimation of two parameters starting from noisy measurements of two scalar outputs. In both these cases, replacing the FOM of cardiac electromechanics with the ANN-based ROM makes it possible to perform in a few hours of computational time the numerical simulations that would be unaffordable if carried out with the FOM, because of their overwhelming computational cost.