Synergistic biophysics and machine learning modeling to rapidly predict cardiac growth probability

• Published in: Computers in biology and medicine Vol. 184; p. 109323
• Main Authors: Jones, Clara E., Oomen, Pim J.A.
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.01.2025; Elsevier Limited
• Subjects: Animals; Bayes Theorem; Bayesian analysis; Biophysics; Biophysics modeling; Calibration; Cardiac mechanics; Computer applications; Computer Simulation; Confidence intervals; Datasets; Dogs; Gaussian process; Growth & remodeling; Heart; Heart - growth & development; Heart - physiology; Humans; Internal Medicine; Learning algorithms; Machine Learning; Mathematical models; Mitral regurgitation; Mitral valve; Mitral Valve Insufficiency - diagnostic imaging; Mitral Valve Insufficiency - physiopathology; Models, Cardiovascular; Other; Probability learning; Regurgitation; Statistical analysis; Synthetic data; Uncertainty; Growth & remodeling; Biophysics modeling; Mitral regurgitation; Cardiac mechanics; Machine learning
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2024.109323

Computational models that can predict growth and remodeling of the heart could have important clinical applications. However, the time it takes to calibrate and run current models while considering data uncertainty and variability makes them impractical for routine clinical use. This study aims to address this need by creating a computational framework to efficiently predict cardiac growth probability. We utilized a biophysics model to rapidly simulate cardiac growth following mitral valve regurgitation (MVR). Here we developed a two-tiered Bayesian History Matching approach augmented with Gaussian process emulators for efficient calibration of model parameters to align with growth outcomes within a 95% confidence interval. We first generated a synthetic data set to assess the accuracy of our framework, and the effect of changes in data uncertainty on growth predictions. We then calibrated our model to match baseline and chronic canine MVR data and used an independent data set to successfully validate the ability of our calibrated model to accurately predict cardiac growth probability. The combined biophysics and machine learning modeling framework we proposed in this study can be easily translated to predict patient-specific cardiac growth. •Cardiac growth is essential for long-term heart failure outcomes.•Combined biophysics and machine learning modeling can predict cardiac growth.•The methods were tested and validated on synthetic and experimental data.•The framework can be easily translated to predict patient-specific outcomes.