Fig. 4

The discrimination and calibration performance of LASSO model. Plot (A) showed the ROC curves of the LASSO model in the training set and validation set, respectively (AUC = 0.7879 versus 0.7994). Calibration curves of the LASSO model in the training set (B) and validation set (C). Calibration curves depicted the calibration of the LASSO model in terms of the agreement between the predicted risk of in-hospital mortality and observed in-hospital mortality. The 45° dotted line represents a perfect prediction, and the blue lines represent the predictive performance of the LASSO model. The closer the violet line fit is to the ideal line, the better the predictive accuracy of the LASSO model is. AUC, area under the curve; LASSO, least absolute shrinkage and selection operator; ROC, receiver operating characteristic