Figure 5
Evaluation of the nomogram model. (A) ROC curves of the nomogram. The area under the ROC curve was 0.96 (95% CI: 0.93–0.98). (B) The calibration curve of the nomogram. It showed that the apparent curve and the bias-corrected curve were close to the ideal curve, which indicated that the predicted probability of death was highly consistent with the actual probability. (C) DCA curves of the nomogram. The threshold probability is 15%–95%, and the nomogram for predicting 30-day mortality has a high net benefit. AUC, area under the curve; ROC, receiver operating characteristic; DCA, decision curve analysis; CI, confidence interval.
