Figure 6

The ROC analysis results from the four diagnostic models calculated from the logistic regression analysis. The performance of each biomarker model was evaluated by the area under the ROC curve (AUC) and the determination of sensitivity and specificity at the optimal cut-off point defined by the minimum distance to the top-left corner. The optimized model was the P4 model with an AUC of 0.937 (95% CI: 0.868–0.976).