基于SEER数据库的胃癌预后列线图模型的构建与验证

Construction and validation of a nomogram model for prognosis of gastric cancer based on SEER database

目的探讨胃癌患者的预后风险因素,构建一个列线图预后预测模型来预测胃癌患者的总生存期(overall survival,OS)。方法基于SEER数据库,对2010年至2015年诊断为胃癌患者数据进行回顾性分析。对纳入变量进行单因素和多因素Cox回归分析,筛选出影响胃癌患者生存的独立危险因素,利用Kaplan-Meier法绘制生存曲线。根据临床经验及统计学结果纳入危险因素,用于构建胃癌患者的预后模型并绘制列线图。采用C-index、ROC曲线和校准曲线评价临床预测模型。结果本研究共纳入3052例胃癌患者。构建了胃癌患者的1年、3年和5年预后预测模型。使用C-index评估列线图模型的准确性,训练集中C-index的结果为0.780(95%CI:0.769~0.793),验证集中C-index的结果为0.763(95%CI:0.743~0.783)。通过ROC曲线评估列线图模型。训练集ROC曲线的1年、3年和5年生存率AUC分别为0.844、0.852和0.858。验证集中ROC曲线的1年、3年和5年生存率AUC分别为0.824、0.829和0.842。训练集及验证集中的校准图也表明该模型具有较高的精度。结论构建的列线图预测模型可以有效预测胃癌患者的OS,有助于指导临床医师个性化预后评估和临床决策。

Objective To investigate the prognostic risk factors of gastric cancer patients and construct a nomogram prognostic prediction model to predict the overall survival(OS)of gastric cancer patients.Methods Based on the SEER database,data on patients with gastric cancer diagnosed from 2010 to 2015 were gathered and retrospectively examined.The factors affecting the survival of patients with gastric cancer were screened out using univariate and multivariate Cox regression analysis,and the Kaplan-Meier method was employed to plot the survival curve.The risk factors were taken into consideration according to clinical experience and statistical results,which were used to construct a prognostic model for gastric cancer patients and to draw a nomogram.The C-index,ROC curve and calibration curve were used to assess the clinical prediction model.Results There were 3052 gastric cancer patients in this study.A nomogram,which was a 1-year,3-year and 5-year prognostic prediction model for patients with gastric cancer,was constructed.The C-index was used to assess the nomogram model′s accuracy,which was 0.780(95%CI:0.769-0.793)in the training set and 0.763(95%CI:0.743-0.783)in the validation set.The ROC curve was used to assess the nomogram model.The area under the 1-year,3-year and 5-year survival curves of the ROC curves in the training set were 0.844,0.852 and 0.858,respectively.The area under the 1-year,3-year and 5-year survival curves of the ROC curves in the validation set were 0.824,0.829 and 0.842,respectively.The training set and verification set′s calibration charts further demonstrated the model′s great accuracy.Conclusion The nomogram prediction model can accurately predict the OS of patients with gastric cancer,which can help guide clinicians in personalized prognostic assessment and clinical decision-making.