Fig. 4

Performance of the PCS-nomogram to predict LNM. a The ROC curves of the PCS-nomogram and the traditional model to predict LNM in the training cohort and the internal and external validation cohorts. b The calibration curves of the PCS-nomogram in the training cohort and the internal and external validation cohorts. c DCA for the PCS-nomogram and the traditional model in each cohort. In the DCA curves, the y-axis measures the net benefit. The red line represents the PCS-nomogram, the blue line represents the traditional model, the gray line represents the assumption that all patients have LNM, and the black line represents the assumption that no patients have LNM. The results showed that if the threshold probability was > 0.10, using the PCS-nomogram to predict LNM could add more benefits than the traditional model. PCS pathomics-collagen signature, LNM lymph node metastasis, AUROC area under the receiver operating characteristic curve, DCA decision curve analysis