InVAErt networks for amortized inference and identifiability analysis of lumped parameter hemodynamic models

TL;DR

This paper introduces inVAErt networks, a neural network framework that improves parameter estimation and identifiability analysis in complex cardiovascular models, addressing challenges of non-identifiability and limited data.

Contribution

The study presents inVAErt networks as a novel data-driven approach for enhanced inverse analysis and identifiability in lumped parameter hemodynamic models.

Findings

Effective in parameter estimation from synthetic and real data

Addresses non-identifiability issues in cardiovascular models

Demonstrates flexibility in handling missing data

Abstract

Estimation of cardiovascular model parameters from electronic health records (EHR) poses a significant challenge primarily due to lack of identifiability. Structural non-identifiability arises when a manifold in the space of parameters is mapped to a common output, while practical non-identifiability can result due to limited data, model misspecification, or noise corruption. To address the resulting ill-posed inverse problem, optimization-based or Bayesian inference approaches typically use regularization, thereby limiting the possibility of discovering multiple solutions. In this study, we use inVAErt networks, a neural network-based, data-driven framework for enhanced digital twin analysis of stiff dynamical systems. We demonstrate the flexibility and effectiveness of inVAErt networks in the context of physiological inversion of a six-compartment lumped parameter hemodynamic model from synthetic data to real data with missing components.