<p>Accurate and rapid characterization of lung mechanics remains a central challenge in respiratory disease management. Physics-informed poroelastic finite-element (FE) models resolve detailed tissue–airflow interactions but are computationally prohibitive for real-time or large-scale clinical applications, while lumped-parameter models sacrifice mechanistic fidelity for efficiency. In this work, we present a porcine-specific, multi-fidelity computational framework that integrates poroelastic FE modeling with machine learning to enable rapid, uncertainty-aware estimation of respiratory compliance (<InlineEquation ID="IEq1"> <EquationSource Format="TEX">${ C}_{\textrm{rs}}$</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>C</mi> <mtext>rs</mtext> </msub> </math></EquationSource> </InlineEquation>) and resistance (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">${ R}_{\textrm{rs}}$</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>R</mi> <mtext>rs</mtext> </msub> </math></EquationSource> </InlineEquation>). High- and low-fidelity simulations are generated from CT-derived porcine lung geometries by sampling a physiologically relevant parameter space, and the resulting pressure–volume dynamics are used in an inverse modeling procedure to infer global respiratory mechanics. A key result is that multi-fidelity Gaussian process (MF-GP) surrogates achieve accurate predictions of <InlineEquation ID="IEq3"> <EquationSource Format="TEX">${ C}_{\textrm{rs}}$</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>C</mi> <mtext>rs</mtext> </msub> </math></EquationSource> </InlineEquation> and <InlineEquation ID="IEq4"> <EquationSource Format="TEX">${ R}_{\textrm{rs}}$</EquationSource> <EquationSource Format="MATHML"><math> <msub> <mi>R</mi> <mtext>rs</mtext> </msub> </math></EquationSource> </InlineEquation> with errors below 5% relative to high-fidelity simulations, while providing computational speedups of over five orders of magnitude. In contrast, neural network (NN) surrogates exhibit relatively poor generalization in the data-scarce regime considered, highlighting the importance of model selection for scientific machine learning under limited high-fidelity data availability. Beyond predictive performance, global sensitivity analysis reveals a clear mechanistic separation in parameter influence: compliance is primarily governed by elastic stiffness and chest-wall coupling, whereas resistance is dominated by permeability. The weak interaction effects observed support an approximately additive response structure, enabling robust parameter identifiability and reduced-order representations of the inverse problem. The framework is validated against independent ventilator measurements from porcine lungs, showing strong agreement within clinically observed ranges. Overall, this study provides new insight into the structure of the inverse problem in poroelastic lung modeling and establishes a computationally efficient pathway for uncertainty-aware prediction and parameter estimation, with potential applications in personalized ventilation and preclinical study design.</p>

A multi-fidelity poroelastic finite element and machine learning framework for characterizing respiratory mechanics in porcine lungs

期刊论文
出版模式：

开放获取
发表日期：

2026年7月1日

查看全文

Edwin E. Aigbokhan,
Olusola A. Olabanjo,
Emmanuel A. Akor,
David W. Kaczka,
Mingchao Cai

摘要

Accurate and rapid characterization of lung mechanics remains a central challenge in respiratory disease management. Physics-informed poroelastic finite-element (FE) models resolve detailed tissue–airflow interactions but are computationally prohibitive for real-time or large-scale clinical applications, while lumped-parameter models sacrifice mechanistic fidelity for efficiency. In this work, we present a porcine-specific, multi-fidelity computational framework that integrates poroelastic FE modeling with machine learning to enable rapid, uncertainty-aware estimation of respiratory compliance ( ${ C}_{\textrm{rs}}$ $C_{rs}$ ) and resistance ( ${ R}_{\textrm{rs}}$ $R_{rs}$ ). High- and low-fidelity simulations are generated from CT-derived porcine lung geometries by sampling a physiologically relevant parameter space, and the resulting pressure–volume dynamics are used in an inverse modeling procedure to infer global respiratory mechanics. A key result is that multi-fidelity Gaussian process (MF-GP) surrogates achieve accurate predictions of ${ C}_{\textrm{rs}}$ $C_{rs}$ and ${ R}_{\textrm{rs}}$ $R_{rs}$ with errors below 5% relative to high-fidelity simulations, while providing computational speedups of over five orders of magnitude. In contrast, neural network (NN) surrogates exhibit relatively poor generalization in the data-scarce regime considered, highlighting the importance of model selection for scientific machine learning under limited high-fidelity data availability. Beyond predictive performance, global sensitivity analysis reveals a clear mechanistic separation in parameter influence: compliance is primarily governed by elastic stiffness and chest-wall coupling, whereas resistance is dominated by permeability. The weak interaction effects observed support an approximately additive response structure, enabling robust parameter identifiability and reduced-order representations of the inverse problem. The framework is validated against independent ventilator measurements from porcine lungs, showing strong agreement within clinically observed ranges. Overall, this study provides new insight into the structure of the inverse problem in poroelastic lung modeling and establishes a computationally efficient pathway for uncertainty-aware prediction and parameter estimation, with potential applications in personalized ventilation and preclinical study design.