大细胞肺癌列线图预后模型构建及验证  

Construction and validation of the nomogram prognostic model of large cell lung cancer

作　　者：崔晓娜 安梦霞 孙继宏 张瀚文 王萍玉 CUI Xiao-na;AN Meng-xia;SUN Ji-hong;ZHANG Han-wen;WANG Ping-yu(School of Public Health and Management,Binzhou Medical College,Yantai,Shandong 264003,China)

机构地区：[1]滨州医学院公共卫生与管理学院,山东烟台264003

出　　处：《现代预防医学》2022年第10期1747-1752,1760,共7页Modern Preventive Medicine

基　　金：国家自然科学基金(81772281);山东省自然科学基金重点项目(ZR2020KH015)

摘　　要：目的探讨大细胞肺癌患者预后影响因素并构建列线图,提高患者生存率。方法下载SEER数据库2010—2015年诊断为大细胞肺癌患者2196例,使用多因素Cox比例风险模型筛选患者预后影响因素并构建列线图模型,C指数和ROC曲线验证模型区分度,校准图验证一致性,决策曲线分析验证临床应用价值。结果年龄、性别、种族、骨转移、肝转移、脑转移、AJCC分期、手术、化疗、肿瘤大小和婚姻是大细胞肺癌患者预后的重要影响因素(P<0.05),训练集和验证集的C指数分别为0.765和0.769,训练集1年和3年AUC分别为0.848(95%CI:0.832~0.865)和0.859(95%CI:0.839~0.877),验证集1年和3年AUC分别为0.840(95%CI:0.810~0.869)和0.857(95%CI:0.823~0.891),表明列线图有较高的区分度,校准图表明其一致性较好,决策曲线分析表明列线图的临床应用价值较高。结论基于大细胞肺癌预后影响因素AJCC分期、手术、化疗等构建的列线图模型,预测价值较高,可评估患者预后,有利于提高患者生存率。Objective To investigate the prognostic factors of large cell lung cancer(CLC)and construct a nomogram to improve the survival rate of patients.Methods Data of 2196 patients diagnosed with large cell lung cancer from 2010 to 2015 were downloaded from SEER database.The multivariate cox proportional risk model was used to screen the prognostic factors of patients and construct the line graph model.C index and ROC curve were used to verify model differentiation,calibration diagram was used to verify consistency,and decision curve analysis was used to verify clinical application value.Results Age,gender,race,bone metastasis,liver metastasis,brain metastasis,AJCC stage,operation,chemotherapy,tumor size and marriage were the important factors influencing prognosis of patients with large cell lung cancer(P<0.05).The C index of training set and validation set was 0.765 and 0.769,respectively.The AUC of 1-year and 3-year training sets were 0.848(95%CI:0.832-0.865)and 0.859(95%CI:0.839-0.877),respectively,and the AUC of 1-year and 3-year validation sets were 0.840(95%CI:0.810-0.869)and 0.857(95%CI:0.823-0.891),respectively,indicating that the nomogram had a high degree of differentiation.The calibration diagram showed good consistency,and the decision curve analysis showed that the nomogram had a high clinical application value.Conclusion Based on the prognostic factors of large cell lung cancer,such as AJCC stage,operation and chemotherapy,the nomogram model has high predictive value and can evaluate the prognosis of patients,which is beneficial to improve the survival rate of patients.

关 键 词：大细胞肺癌 预后模型 列线图 决策曲线分析 

分 类 号：R743.2[医药卫生—神经病学与精神病学]