Nomograms for Predicting Cancer-Specific Survival of Patients with Gingiva Squamous Cell Carcinoma:A Population-Based Study

The use of the traditional American Joint Committee on Cancer(AJCC)staging system alone has limitations in predicting the survival of gingiva squamous cell carcinoma(GSCC)patients.We aimed to establish a comprehensive prognostic nomogram with a prognostic value similar to the AJCC system.Methods:Patients were identified from SEER database.Variables were selected by a backward stepwise selection method in a Cox regression model.A nomogram was used to predict cancer-specific survival rates for 3,5 and 10 years in patients with GSCC.Several basic features of model validation were used to evaluate the performance of the survival model:consistency index(C-index),receiver operating characteristic(ROC)curve,calibration chart,net weight classification improvement(NRI),comprehensive discriminant improvement(IDI)and decision curve analysis(DCA).Results:Multivariate analyses revealed that age,race,marital status,insurance,AJCC stage,pathology grade and surgery were risk factors for survival.In particular,the C-index,the area under the ROC curve(AUC)and the calibration plots showed good performance of the nomogram.Compared to the AJCC system,NRI and IDI showed that the nomogram has improved performance.Finally,the nomogram's 3-year and 5-year and 10-year DCA curves yield net benefits higher than traditional AJCC,whether training set or a validation set.Conclusion:We developed and validated the first GSCC prognosis nomogram,which has a better prognostic value than the separate AJCC staging system.Overall,the nomogram of this study is a valuable tool for clinical practice to consult patients and understand their risk for the next 3,5 and 10 years.