FIG 3.
Four model performance in the training and validation cohorts. (A) Comparison of the AUC values between 4 models based on risk scores (red, LR; blue, RF; yellow, SVM; dark, KNN) in the training cohorts. (B) The AUC values of the LR model in the independent validation cohorts. The 95% confidence interval of AUC is also shown in the legend area.