Fig. 4

Model Interpretation by SHAP. a The overall contribution of each feature to the model prediction classification (class 0: non-response, class 1: response), in order of importance. b A detailed contribution to the class 0 model prediction, where the colors represent the magnitude of the feature values. c The detailed contribution to the class 1 model prediction. d Explanation of how features affect the model's predictions for a single sample, where the results show that this patient would be effectively relieved by performing CCRT. e An example that a model predicts that a patient will not achieve effective remission with CCRT. f Feature dependency visualization by interaction values between features. g Heat map of Pearson correlation coefficients between features