Fig. 4

(A) Comparison of classification accuracy of the models on the training set. (B) Comparison of classification accuracy of the models on the test set. (C) ROC curves of the models on the test set. (D) P–R curves of the models on the test set. ROC curve receiver operating characteristic curve, P-R curve precision-recall curve, AUC area under the curve. *p < 0.05; **p < 0.01; NS not significant.