Physics-Informed Emulation Enables Fast Cardiovascular Parameter Estimation

William Ryan et al. (Int J Numer Method Biomed Eng., Feb 2026) develop a physics-informed neural network emulator of systemic circulation to enable fast patient-specific parameter estimation and inverse uncertainty quantification. Trained surrogates predict flow and pressure waveforms far faster than numerical solvers and are evaluated against state-of-the-art ML methods. Applied to clinical data from four Double Outlet Right Ventricle (DORV) patients, the framework shows accuracy and efficiency gains relevant to clinical calibration.