Figure 2
From: Urine metabolomics based prediction model approach for radiation exposure
The ROC analysis results from the four prediction models calculated from the logistic regression analysis. The diagnostic performance of each biomarker model was assessed by the area under the ROC curve (AUC) and the determination of sensitivity and specificity at the optimal cut-off was determined using the Youden index (J). The optimized model was the P4 model with an AUC of 0.999 (95% CI 0.933–1.00).
