Calibration curves of the nine predictive models

Calibration curves depicting the agreement between the predicted probability and the observed outcome proportion for the nine models. ​​Training cohort​​: A: 1 year.B:3 years.C:5 years. ​​Validation cohort: D:1 year. E:3 years. F: 5 years. The diagonal dashed line represents perfect calibration. A curve closer to the diagonal indicates better calibration performance, meaning the predicted risks are more accurate. Abbreviations：RSF: Random Survival Forest；GBM: Gradient Boosting Machine; CoxBoost: Cox regression with Gradient Boosting; SurvivalSVM:Survival Support Vector Machine; XGBoost: Extreme Gradient Boosting; SuperPC: Super Principal Component Regression; PLSR-Cox: Partial Least Squares Cox Regression.