Skip to main content
. 2020 Sep 7;26(33):5008–5021. doi: 10.3748/wjg.v26.i33.5008

Figure 6.

Figure 6

Receiver operating characteristic curves of the models in the training and validation cohorts. A: In the training set, the combined model [area under the curve under the curve (AUC) = 0.842] achieved a better performance than the Rad-score (AUC = 0.709) and the clinical model containing T-stage and N-stage (AUC = 0.782); B: In the validation set, the AUCs of the Rad-score, the clinical model, and the combined model were 0.687, 0.766, and 0.802, respectively.