Site specific prediction of atherosclerotic plaque progression using computational biomechanics and machine learning

Atheromatic plaque progression is considered as a typical pathological condition of arteries and although atherosclerosis is considered as a systemic inflammatory disorder, atheromatic plaque is not uniformly distributed in the arterial tree. Except for the systematic atherosclerosis risk factors, biomechanical forces, LDL concentration and artery geometry contribute to the atherogenesis and atherosclerotic plaque evolution. In this study, we calculate biomechanical forces acting within the artery and we develop a machine learning model for the prediction of atheromatic plaque progression. 1018 coronary sites of 3 mm, derived by 40 individuals, are utilized to develop the model and after the implementation of 4 different tree based prediction schemes, we achieve a prediction accuracy of 0.84. The best accuracy was achieved by the implementation of a tree-based classifier, the Random Forest classifier, after a ranking feature selection methodology. The novel aspect of the proposed methodology is the implementation of machine learning models in order to address the cardiovascular data modeling, aiming to predict the occurrence of an outcome and not to investigate the association of input features.