基于seer数据库肺癌脑转移预测模型的构建  

Nomogram for predicting brain metastasis in lung cancer based on SEER database

作　　者：任良玉 王勇[1] 武沛佩 徐爱晖[1] REN Liang-yu;WANG Yong;WU Pei-pei;XU Ai-hui(Department of Respiratory and Critical Care Medicine,the First Affiliated Hospital of Anhui Medical University,Hefei,Anhui 230022,China)

机构地区：[1]安徽医科大学第一附属医院呼吸与危重症医学科,安徽合肥230022

出　　处：《临床肺科杂志》2021年第7期1063-1069,共7页Journal of Clinical Pulmonary Medicine

基　　金：国家公益性行业科研专项(No.201302003)。

摘　　要：目的全球范围内,肺癌的发病率高居首位,肺癌的脑转移也越来越引起人们的重视,而预测脑转移的模型很少。本研究拟建立一个全新的模型和列线图来预测肺癌患者脑转移的发生概率,有助于临床决策并使得患者受益。方法本研究从SEER数据库中提取58514例肺癌病例,并按照7:3的比率将患者随机分为训练队列和验证队列,确定并整合风险因素以构建列线图,并使用SEER数据库对该模型进行内部验证。结果本研究纳入了14个独立的预后因素,校准曲线显示出良好的一致性,训练集中的C指数为0.826(95%CI:0.654~0.844),验证集中为0.829(95%CI:0.666~0.846)。结论本研究建立了实用的列线图来预测肺癌患者的脑转移,能较好指导临床决策。Objective Nowadays,the incidence of lung cancer is still the highest,and brain metastasis of lung cancer is attracting more and more attention,but there are few models to predict brain metastasis.We conducted this study to recommend a novel model and nomogram to predict the probability of brain metastases in lung cancer patients and to help physicians make better clinical decisions that benefit patients.Methods A total of 58514 lung cancer cases were extracted from the SEER database.The patients were randomly divided into two cohorts,the training cohort and the validation cohort,at a ratio of 7:3.The risk factors were identified and integrated to build a nomogram.The model was subjected to internal validation with the SEER database.Results 14 independent prognostic factors were identified and integrated into the model.The calibration curves showed good agreement.The C-indexes in the training group was 0.826(95%CI:0.654~0.844),and 0.829 in the validation group(95%CI:0.666~0.846).Conclusion In this study,a practical nomogram is established to predict brain metastasis in lung cancer patients,which can help make better clinical decision.

关 键 词：脑转移 预后因素 肺癌 

分 类 号：R734.2[医药卫生—肿瘤] TP311.13[医药卫生—临床医学]