Fig. 2
Construction of a risk prognostic model and survival prediction validation in training and testing cohorts. (a) Univariate Cox regression showed 39 PRLs related to osteosarcoma survival (P < 0.05). (b,c) Lasso regression for PRLs in univariate Cox regression. Coefficients refer to the risk coefficient corresponding to each gene. (d–f) Distribution of risk score, survival status, and heatmap of the two PRLs signature in training cohort. (g–i) Distribution of risk score, survival status, and heatmap of the two PRLs signature in testing cohort. (j) The Kaplan–Meier survival curve effectively demonstrates that patients in the high-risk group exhibited a substantially lower overall survival rate compared to those in the low-risk group in training cohort. (k) Time-dependent ROC curves, 1 year (AUC = 0.904), 3 years (AUC = 0.817), and 5 years (AUC = 0.837) in training cohort. (l) The Kaplan–Meier survival curve effectively demonstrates that patients in the high-risk group exhibited a substantially lower overall survival rate compared to those in the low-risk group in testing cohort. (m) Time-dependent ROC curves, 1 year (AUC = 0.894, 3 years (AUC = 0.742), and 5 years (AUC = 0.714) in testing cohort.
