Multi-fidelity model rapidly estimates lung compliance and resistance in porcine lungs with <5% error

In a computational study, a multi-fidelity Gaussian process surrogate estimated porcine respiratory compliance and resistance from CT-derived models with errors below 5% relative to high-fidelity simulations, achieving over 100,000-fold speedup. Neural networks showed poor gener…

• Design: Computational study using multi-fidelity poroelastic finite-element modeling and machine learning on CT-derived porcine lung geometries (sample size unspecified).
• Key findings: Compliance was driven by elastic stiffness/chest-wall coupling; resistance was permeability-dominant. Global sensitivity analysis showed weak interaction effects, supporting an additive response structure.
• Limitation: Framework validated only in ex vivo porcine lungs; clinical translation to human respiratory disease management requires prospective in vivo validation.

RadPigeon summaries are original and for information only. They are not clinical advice.