Modified Logistic Regression Models Using Gene Coexpression and Clinical Features to Predict Prostate Cancer Progression
Figure 1
AUC boxplots for 100 tenfold cross validations of 16 models that include TSP-selected genes. The x-axis is the index of 16 models listed in Table 1, and the y-axis is the AUC values. The red star denotes the corresponding AUC values of the validation dataset that uses the best logistic regression models from the learning dataset. (a) Models that included one pair of TSP-selected genes and (b) those that included two such gene pairs.
