Figure 4. The immunoscore for each patient, the time-dependent ROC curve, and the Kaplan–Meier curves in (A–C) the training cohort and (D–F) the validation cohort. The 2-, 3-, and 5-year AUCs were used in the training cohort, and the 1-, 2-, and 3-year AUCs were used in the validation cohort to evaluate the accuracy of the prognostic model. The log-rank test was performed to analyse survival status.