基于SEER数据库的儿童青少年室管膜瘤预后Nomogram模型的构建和验证

目的 基于SEER数据库构建并验证儿童青少年室管膜瘤的Nomogram预测模型.方法 获取1975—2016年SEER数据库临床病理信息,单变量和多变量Cox比例风险回归模型确定潜在的预测因素,构建Nomogram模型预测5年和10年总生存率.通过一致性指数、受试者工作特征曲线和校准曲线值来评估列线图的辨别能力.决策曲...

Establishment and Validation of A Prognostic Nomogram for Pediatric Ependymoma Based on SEER Database

Objective To establish and validate a Nomogram for predicting the survival of patients with pediatric ependymoma based on SEER database.Methods We collected the clinicopathological data from 1975 to 2016 in the SEER database.Univariate and multivariate Cox proportional hazard regression models were used to identify potential predictors.A Nomogram was constructed to predict 5-and 10-year overall survival of patients with pediatric ependymoma.The consistency index(C-index),receiver operating characteristic curve and calibration curve were used to verify the discrimination and accuracy of the Nomogram.The decision curve analysis was performed to verify the clinical applicability of the Nomogram.Results A Nomogram model was established based on multivariate Cox proportional hazards model of training set.C-index values of the Nomogram were 0.713(95%CI:0.680-0.747)and 0.734(95%CI:0.681-0.787)in the training and validation sets,respectively.ROC curves also showed good discrimination in the training set.The calibration curves showed satisfactory consistency between Nomogram and ideal models.The decision curve analysis demonstrated the considerable clinical usefulness of the Nomogram.Conclusion The Nomogram model is constructed based on age at diagnosis,gender,race,primary tumor sites,tumor grade,surgery treatment and SEER registry to predict the survival of patients with pediatric ependymoma.It has good discrimination and accuracy degree,providing useful guidance to make more accurate and personalized survival prediction for patients in clinic.