Figure 4
Two receiver operating characteristic (ROC) curves are presented side by side, each depicting the performance of two different models, Model A and Model B. Each ROC curve graphically represents the diagnostic ability of the binary classifiers for different classes. The x-axis represents the false positive rate (FPR) and the y-axis represents the true positive rate (TPR). The diagonal dashed line represents the line of no-discrimination where the true positive rate equals the false positive rate. Panel A: The ROC curve for Model A shows four classes, each with an area under the curve (AUC) of 1.00, indicating perfect classification. The classes are color-coded: Class 0 in blue, Class 1 in orange, Class 2 in green, and Class 3 in red. Panel B: The ROC curve for Model B also shows four classes. Class 0 and Classes 2 and 3 have an AUC of 1.00, while Class 1 has an AUC of 0.99, indicating very high classification performance. The classes are similarly color-coded as in Panel A.The receiver operating characteristic (ROC) curves of the models