Fig. 2

The ROC curve of the nomogram. (A) The ROC curve of the nomogram in the training cohort is 0.846 (95% CI: 0.817–0.875), The optimal threshold (0.519) occurs when the sensitivity is 0.677 and the specificity is 0.907; (B) the ROC curve of the nomogram in the validation cohort is 0.798 (95% CI: 0.744–0.852). The optimal threshold occurs (0.519) when the sensitivity is 0.674 and the specificity is 0.850. AUC, area under the curve; ROC, receiver operating characteristic