非小细胞肺癌合并脑转移患者预后模型的构建研究

Construction of prognostic model of non-small cell lung cancer patients with brain metastases

目的研究旨在评估新诊断非小细胞肺癌(NSCLC)合并脑转移患者的预后因素,并构建列线图来预测总生存期(OS)。方法从SEER数据库中纳入2010—2016年新诊断为NSCLC伴脑转移患者,随机以7∶3分为建模组和验证组;采用Cox比例风险回归分析NSCLC合并脑转移患者的独立预后因素;使用R软件构建列线图并对其进行区分度、一致性、有效性评价,最终绘制1~3年生存曲线。结果6102例合并脑转移的NSCLC患者被纳入分析,年龄、种族、性别、组织学类型、肝转移、肺转移、骨转移、Grade分级、T分期、N分期、手术、化疗及放疗是NSCLC合并脑转移患者的独立预后因素。综合分析建立列线图,通过区分度、一致性、有效性评价验证,该临床预测模型在预测预后方面具有较好的效果。结论通过构建临床预测模型,可以有效预测NSCLC合并脑转移患者个体的总生存期,对临床医生和患者具有指导意义。

Objective Patients with non-small cell lung cancer(NSCLC)complicated with brain metastases(BM)have poor prognosis.This study aimed to evaluate the prognostic factors of BM in newly diagnosed NSCLC patients and construct a nomogram to predict the overall survival(OS).Methods We included NSCLC patients with BM diagnosed from 2010 to 2016 in SEER and they were randomly divided into the modeling group and the validation group at 7∶3.The independent prognostic factors for NSCLC with BM were determined by Cox proportional hazard regression analysis.R software was used to construct a nomogram and evaluate its differentiation,consistency and effectiveness,and finally draw a 1-3-year survival curve.Results We finally included 6102 NSCLC patients with BM for analysis.Age,race,gender,histologic type,liver metastasis,lung metastasis,bone metastasis,Grade grading,T staging,N staging,surgery,chemotherapy and radiotherapy were identified as the prognostic factors for NSCLC with BM and integrated to establish the nomogram.The calibration,receiver operating characteristic curve,and decision curve analyses also showed that the clinical prediction model performed satisfactorily in predicting prognosis.Conclusion The construction of a clinical prediction model could effectively predict the overall survival of patients with NSCLC with BM,which has guiding significance for clinicians and patients.