A comparative analysis of metamodels for 0D cardiovascular models, and pipeline for sensitivity analysis, parameter estimation, and uncertainty quantification

TL;DR

This paper compares different metamodeling strategies for 0D cardiovascular models, demonstrating a pipeline that enhances sensitivity analysis, parameter estimation, and uncertainty quantification, with neural networks showing superior performance.

Contribution

It introduces a comprehensive pipeline for building and applying metamodels to 0D cardiovascular models, highlighting neural networks as the most effective approach.

Findings

Neural networks outperform polynomial chaos and Gaussian processes in accuracy and efficiency.

The pipeline successfully integrates metamodels for sensitivity, estimation, and uncertainty tasks.

Neural networks enable rapid and reliable analysis of complex cardiovascular models.

Abstract

Zero-dimensional (0D) cardiovascular models are reduced-order models used to study global circulation dynamics and transport. They provide estimates of biomarkers (such as pressure, flow rates, and concentrations) for surgery planning and boundary conditions for high-fidelity 3D models. Although their computational cost is low, tasks like parameter estimation and uncertainty quantification require many model evaluations, making them computationally expensive. This motivates building metamodels. In this work, we propose a pipeline from 0D models to metamodel building for tasks such as sensitivity analysis, parameter estimation, and uncertainty quantification. Three strategies are explored: Neural Networks, Polynomial Chaos Expansion, and Gaussian Processes, applied to three different 0D models. The first model predicts portal vein pressure after surgery, considering liver hemodynamics and global circulation. The second simulates whole-body circulation under pulmonary arterial hypertension before and after shunt insertion. The third assesses organ blood perfusion after revascularization surgery, focusing on contrast agent transport, requiring specific metamodel treatment. Metamodels are trained and tested on synthetic data. Neural networks proved the most efficient in terms of result quality, computational time, and ease for parameter estimation, sensitivity analysis, and uncertainty quantification. Finally, we demonstrate the full pipeline with a neural network as the emulator.