Fig. 2From: Predicting plaque vulnerability change using intravascular ultrasound + optical coherence tomography image-based fluid–structure interaction models and machine learning methods with patient follow-up data: a feasibility studyROC obtained by optimal combinational-factor predictors and machine learning method with best performance for prediction of three morphological indices. a ROC of combinational-factor predictor (LP, critical WSS, cap PWS, cap PWSn and cap WSS) using SVM for ΔLPI prediction. b ROC of combinational-factor predictor (MinCT, MeanCT, critical PWS, cap PWS and cap PWSn) using DA for ΔLPI prediction. c ROC of combinational-factor predictor (MinCT, plaque area and critical PWS) using DA for ΔMPVI predictionBack to article page