Modified Logistic Regression Models Using Gene Coexpression and Clinical Features to Predict Prostate Cancer Progression

Figure 2

The AUCs of the 16 best models from the validation dataset. The x-axis is the index of the 16 models listed in Table 1, and the y-axis is the AUC values. The blue line shows the AUCs from the models with one TSP-selected gene pair, and the black line shows those from models with two TSP-selected gene pairs. The points circled in red are the AUCs in the 8 models that included the Gleason score as a variable.