健康指数指标筛选的因果推断方法  

Causal inference methodology for the screening of indicators for health indices

作　　者：刘新辉 李洪凯 王丽洁 刘爱玲[3] 齐越 孙珊珊[4] 张蓝方 季怀君 刘贵元[7] 赵欢 姜轶男 李静宜 宋成村[5] 于鑫 杨柳[5] 于进超[7] 冯虎 杨福俊[4] 薛付忠 LIU Xin-hui;LI Hong-kai;WANG Li-jie;LIU Ai-ling;QI Yue;SUN Shan-shan;ZHANG Lan-fang;JI Huai-jun;LIU Gui-yuan;ZHAO Huan;JIANG Yi-nan;LI Jing-yi;SONG Cheng-cun;YU Xin;YANG Liu;YU Jin-chao;FENG Hu;YANG Fu-jun;XUE Fu-zhong(Department of Biostatistics,School of Public Health,Cheeloo College of Medicine,Shandong University,Jinan 250012,China;National Institute of Health Data Science of China,Jinan 250003,China;Department of Pulmonary and Critical Care Medicine,Weihai Municipal Hospital,Weihai 264299,China;Department of Oncology,Weihai Municipal Hospital,Weihai 264299,China;Department of Chemotherapy,Weihai Municipal Hospital,Weihai 264299,China;Department of Thoracic Surgery,Weihai Municipal Hospital,Weihai 264299,China;Department of Radiology,Weihai Municipal Hospital,Weihai 264299,China;Department of Oncology,The Second Medical College of Binzhou Medical University,Binzhou 256699,China;Department of Radiotherapy,Weihai Municipal Hospital,Weihai 264299,China)

机构地区：[1]山东大学齐鲁医学院公共卫生学院生物统计学系,济南250012 [2]国家健康医疗大数据研究院,济南250003 [3]威海市立医院呼吸与危重症医学科,威海264299 [4]威海市立医院肿瘤综合治疗科,威海264299 [5]威海市立医院化疗科,威海264299 [6]威海市立医院胸外科,威海264299 [7]威海市立医院影像科,威海264299 [8]滨州医学院第二临床医学院肿瘤综合科,滨州256699 [9]威海市立医院放疗科,威海264299

出　　处：《中华疾病控制杂志》2022年第10期1180-1186,1216,共8页Chinese Journal of Disease Control & Prevention

基　　金：国家重点研发计划(2020YFC2003500)。

摘　　要：健康指数体系的构建与发展对于推动健康中国目标的实现具有重要的战略意义。从现实世界数据入手,通过一系列的因果推断方法,筛选和确定对健康/疾病结局具有确凿因果关系且可干预的健康指数指标,从而为健康/疾病管理提供更贴近实践、更有价值的现实世界证据是至关重要的。本文针对健康指数构建的循证医学需求,介绍了目前常用的现实世界研究中人群水平评估的因果推断方法,为健康指数指标筛选提供方法支撑。The construction and development of the health index system have important strategic significance for promoting the realization of the Healthy China initiative.Starting from the real-world data,it is essential to screen indicators for health indices that are definite causes of diseases and can be prevented through a series of causal inference methods.This can provide valuable real-world evidence that is closer to the practice of health/disease management.According to the need for evidence-based medicine for health index construction,this paper introduces population-level causal effect estimation methods that are widely used in real-world studies,aiming at providing methodological support for the screen of indicators for health index.

关 键 词：现实世界数据 健康指数 因果推断 混杂偏倚 

分 类 号：R181.2[医药卫生—流行病学]