Figure 4 Construction and validation of a nomogram model predicting OS in HNSCC patients. (A) Univariable Cox regression forest plot of clinical features and a novel risk score in predicting OS. (B) Multivariable Cox regression forest plot incorporating the same predictors. (C) Time–dependent ROC curves of the risk score for survival prediction. Shaded bands represent 95% confidence intervals. (D) Performance metrics of the risk–score model at 1-, 3-, and 5-year follow-up. (E) Comparison of the 1-year AUC for different variables in predicting OS. (F) Nomogram for predicting 1-, 3-, and 5-year OS. (G) Calibration curves of the nomogram–predicted survival versus observed survival. (H) Kaplan-Meier survival curves stratified by nomogram risk quartiles. OS – overall survival; HNSCC – head and neck squamous cell carcinoma; ROC – receiver operating characteristic; AUC – area under the curve.