Fig. 5

Construction of risk scoring model. A The penalty coefficient of the minimum tenfold cross-validation error point was calculated to determine the corresponding model gene. B Determination of model gene coefficients. C–E Based on the optimal cut-off value, patients in the meta-cohort were divided into high- and low-risk score groups (C); the survival status distribution (D), and model gene expression (b) in high- and low-risk score groups. F Survival analysis between high- and low-risk score groups. G time-dependent ROC curve analysis of risk scores in the meta cohort