基于SEER数据库构建转移性乳腺癌患者的生存预测模型

Prognostic nomogram for patients with metastatic breast cancer:a study based-SEER database

目的探讨影响初诊转移性乳腺癌患者预后的风险因素并构建生存预测模型。方法通过SEER数据库收集2010–2013年期间的初诊转移性乳腺癌患者并采用R软件随机分为建模组与验模组。通过SPSS软件使用log-rank法比较建模组中不同转移部位的转移性乳腺癌患者的生存预后并制作Kaplan-Meier生存曲线。采用单因素分析影响建模组初诊转移性乳腺癌患者预后的相关因素,再通过多因素Cox比例风险模型分析有意义的因素以筛选出影响3年总生存率的独立风险因素并构建nomogram预测模型,利用一致性指数(C指数)评估其预测价值并用校正曲线对nomogram预测模型进行内部(建模组数据)与外部(验模组数据)验证。结果共收集到3288例转移性乳腺癌患者,其中建模组2304例,验模组984例。建模组和验模组整体划分符合简单随机分组,2组资料具有可比性。建模组与验模组中位随访时间均为34个月。多因素Cox比例风险模型分析结果显示,建模组患者的年龄大、黑人、组织学分级高、未手术、ER、PR、HER-2阴性表达以及骨、脑、肝、肺转移是转移性乳腺癌患者3年总生存率的危险因素(P<0.05),这些因素均被用于构建nomogram预测模型,其验证结果表明,建模组和验模组的C指数分别为0.704[95%CI为(0.691,0.717)]和0.691[95%CI为(0.671,0.711)],2组的校正曲线均靠近理想的45°参考线且表现出良好的一致性。结论本研究构建的nomogram预测模型具有良好的预测价值,可对转移性乳腺癌患者3年生存率作出较准确的评估,有利于临床对转移性乳腺癌患者选择个性化治疗。

Objective To explore the risk factors affecting the prognosis of patients with metastatic breast cancer(MBC)and construct a nomogram survival prediction model.Methods The patients with MBC from 2010 to 2013 werecollected from surveillance,epidemiology,and end results(SEER)database,then were randomly divided into traininggroup and validation group by R software.SPSS software was used to compare the survival and prognosis of MBC patientswith different metastatic sites in the training group by log-rank method and construct the Kaplan-Meier survival curve.The Cox proportional hazards model was used to analyze the factors of 3-year overall survival,then construct a nomogramsurvival prediction model by the independent prognostic factors.The C-index was used to evaluate its predictive value andthe calibration curve was used to verify the nomogram survival prediction model by internal and external calibrationgraph.Results A total of 3288 patients with MBC were collected,including 2304 cases in the training group and 984cases in the validation group.The data of the two groups were comparable.The median follow-up time of traininggroup and validation group was 34 months and 34 months,respectively.In the training group,the results of Coxproportional hazards model showed that the older,black race,higher histological grading,without operation,ER(–),PR(–),HER-2(–),and metastases of bone,brain,liver and lung were the risk factors of survival prognosis(P<0.05)andconstructed the nomogram survival prediction model with these independent prognostic factors.The nomogram survival prediction showed a good accuracy with C-index of 0.704[95%CI(0.691,0.717)]in internal validation(training group)and C-index of 0.691[95%CI(0.671,0.711)]in external validation(validation group)in predicting 3-year overall survival.All calibration curves showed excellent consistency.Conclusion Nomogram for predicting 3-year overall survival ofpatients with MBC in this study has a good predictive capability,and it is conducive to development of individualizedclinical treatment.