Figure 5.

Prognostic features related to disulfidptosis constructed through machine learning-based integration and their prognostic value. (A) 84 integrated prediction models based on machine learning were fitted using 10-fold cross-validation. The C-index was computed for each model in both the training and validation cohorts, which included TCGA-BLCA, iMvigor210, and GSE13507 cohorts. (B) The number of trees determined by minimum error. (C) Importance of the four most valuable genes based on the RSF algorithm. (D–F) Kaplan-Meier survival curves of overall survival (OS) for high-risk and low-risk groups of patients in the iMvigor210, TCGA-BLCA, and GSE13507 cohorts, respectively. (G) Kaplan-Meier survival curve of progression-free survival (PFS) for high-risk and low-risk groups of patients in the TCGA-BLCA cohort.