基于群数据科学研究的报告规范:TRIPOD‑Cluster指南清单解读及拓展  

Reporting studies involving cluster data:interpretation and extension of the TRIPOD‑Cluster checklist

作　　者：韩莎莎 吴鹏[4] 王则一 崔逸凡 杨浩翔 周正元 Larry Han 杨林 贾金柱 邵瑞太 王辰 Han Shasha;Wu Peng;Wang Zeyi;Cui Yifan;Yang Haoxiang;Zhou Zhengyuan;Larry Han;Yang Lin;Jia Jinzhu;Shao Ruitai;Wang Chen(School of Population Medicine and Public Health,Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China;State Key Laboratory of Respiratory Health and Multimorbidity,Beijing 100730,China;Key Laboratory of Pathogen Infection Prevention and Control(Peking Union Medical College),Ministry of Education,Beijing 100730,China;School of Mathematics and Statistics,Beijing Technology and Business University,Beijing 100048,China;School of Public Health,University of California,Berkeley,Berkeley 94720,USA;Center for Data Science,Zhejiang Univerisity,Hangzhou 310058,China;School of Data Science,the Chinese University of Hong Kong,Shenzhen,Shenzhen 518172,China;Stern School of Business,New York University,New York 10012,USA;Center for Data Science,New York University,New York 10012,USA;Department of Computer Science,Tandon School of Engineering,New York University,New York 10012,USA;Department of Biostatistics,Harvard T.H.Chan School of Public Health,Boston 02115,USA;Department of Electrical and Computer Engineering,University of California,Los Angeles,Los Angeles 90095,USA;Department of Biostatistics,School of Public Health,Peking University,Beijing 100191,China;Chinese Academy of Medical Sciences&Peking Union Medical College,Beijing 100730,China)

机构地区：[1]中国医学科学院北京协和医学院群医学与公共卫生学院,北京100730 [2]呼吸和共病全国重点实验室,北京100730 [3]病原体感染防控教育部重点实验室(北京协和医学院),北京100730 [4]北京工商大学数学与统计学院,北京100048 [5]加州大学伯克利分校公共卫生学院,伯克利94720 [6]浙江大学数据科学研究中心,杭州310058 [7]香港中文大学(深圳)数据科学学院,深圳518172 [8]纽约大学斯特恩商学院,纽约10012 [9]纽约大学数据科学中心,纽约10012 [10]纽约大学坦顿工程学院计算机科学系,纽约10012 [11]哈佛大学公共卫生学院生物统计学系,波士顿02115 [12]加州大学洛杉矶分校电气与计算机工程系,洛杉矶90095 [13]北京大学公共卫生学院生物统计系,北京100191 [14]中国医学科学院北京协和医学院,北京100730

出　　处：《数字医学与健康》2023年第1期12-21,共10页DIGITAL MEDICINE AND HEALTH

基　　金：中国医学科学院创新工程项目(2023‑I2M‑3‑008);北京工商大学学科建设经费(STKY202301)。

摘　　要：基于群数据的科学研究在医学健康照护领域备受关注。群数据指由多个数据集组成的数据集群。群数据具有明显的群特性,即不同数据集间个体的异质性。为了规范基于群数据的研究报告模式,研究人员于2022年11月在The BMJ发表了“Transparent reporting of multivariable prediction models developed or validated using clustered data:TRIPOD‑Cluster checklist”(TRIPOD‑Cluster指南清单)。本文对该指南清单的关键内容进行了解读和评述,旨在促进对该指南清单的正确理解和应用。同时,从基于群数据模型的异质性和因果可解释性两个方面对该指南清单进行了拓展和延伸。There is increasing interest of medical and healthcare researchers in utilizing clustered data for scientific studies.Clustered data refers to multiple datasets that exhibit distinct group characteristics,i.e.the heterogeneity,of individual datasets.To facilitate accurate reporting of such studies,a checklist named"Transparent Reporting of Multivariable Prediction Models Developed or Validated Using Clustered Data:TRIPOD‑Cluster"was published in The BMJ in November 2022.This paper presents a comprehensive analysis of the checklist′s key components,aiding researchers in understanding and correctly applying it,and addresses the challenges associated with heterogeneity in clustered data models and the interpretability of causal relationships,thereby enhancing the checklist′s practicality and relevance.

关 键 词：群数据 研究报告规范 TRIPOD‑Cluster 异质性 因果可解释性 

分 类 号：R-05[医药卫生]