Fig. 7

Construction and evaluation of the prostate cancer risk prediction model in TCGA. a Overall survival in univariate Cox regression of target genes. b Lasso regression for genes in univariate Cox regression. c The horizontal axis represents the samples, and the vertical axis represents risk scores (top), overall survival (middle), and target genes (bottom). d The heatmap shows the expression of the 5 genes in high-risk and low-risk groups. The distribution of clinic-pathological characteristics was compared between the high-risk and low-risk groups. *P < 0.05, **P < 0.01 and ***P < 0.001. e Univariate and multivariate Cox regression analysis of the clinic-pathological factors (including risk score) related to overall survival. f ROC curve showed the predictive efficiency of the risk score. g Kaplan–Meier overall survival curve for patients with high-risk group and low-risk group. h The expression of genes in lasso regression related to clinic-pathological factors