基于SEER数据库的鼻咽癌患者预后预测模型的构建及验证OA

Objective To analyze the independent prognostic factors of patients with nasopharyngeal carcinoma by using the Surveillance,Epidemiology and End Results(SEER)database,and to establish and verify the prognostic prediction model,so as to evaluate the prognosis of patients and provide the basis for in-dividualized treatment.Methods The medical records of patients diagnosed with nasopharyngeal carcinoma from 2010 to 2018 in the SEER database was retrospectively retrieved.The patients were divided into SEER training set and SEER validation set at a ratio of 7∶3.The baseline characteristics of patients in the SEER training set and SEER validation set were compared.The independent prognostic factors of patients with naso-pharyngeal carcinoma were determined by univariate and multivariate Cox proportional hazard regression model.The 1-,3-,and 5-year overall survival(OS)visual nomogram of patients with nasopharyngeal carcino-ma was constructed using R language to predict the 1-,3-,and 5-year death risk of patients.The consistency index(C-index),receiver operating characteristic(ROC)curve and calibration curve were used to verify the predictive ability of the model.Results A total of 1 602 patients with nasopharyngeal carcinoma were includ-ed.Age,Marital status,clinical Stage,M stage and radiotherapy were independent prognostic factors of OS(P<0.05).The OS nomogram of patients with nasopharyngeal carcinoma was constructed according to the obtained independent prognostic factors.The C-index in the SEER training set was 0.717,and the area under the ROC curve(AUC)of 1-,3-,and 5-year survival rates was 0.772,0.760 and 0.758,respectively.The C-in-dex in the SEER validation set was 0.748,and the AUC of 1-,3-,and 5-year survival rates were 0.805,0.767,and 0.744,respectively.The calibration curve and the standard reference curve overlapped more.Conclusion The predictive model based on SEER database can better predict the prognosis of patients with nasopharyngeal carcinoma.