Fig. 3

Performance evaluation on the validation dataset. a, b ROC curve and AUC of SVM, LR, GBDT, KNN, and NN in internal validation cohort and external validation cohort, respectively. c, d KM curve of low-risk and high-risk subgroup predicted by SVM model in internal validation cohort and external validation cohort, respectively. The light red or blue areas refer to the 95% confidence interval. p value is computed by log-rank test. Hazard ratio (HR) and its 95% confidence interval are obtained with univariate Cox model. SVM, supported vector machine. LR, logistic regression. GBDT, gradient boosted decision tree. KNN, k-nearest neighbor. NN, neural network. HR, hazard ratio