摘要
目的系统分析当前健康体检数据的数据特征,利用Excel和SAS软件宏过程实现数据预处理。方法利用某地市级三甲医院2017年10月至2020年12月健康体检数据平台中的健康体检数据,通过数据梳理总结当前体检数据的特征,制定相应的预处理规则,并基于Excel和SAS软件提出具体数据预处理方案、操作流程及宏代码。结果通过Excel和SAS软件进行了健康体检数据的批量列名转换,使其符合SAS软件变量名命名规则;实现了多个不同结构的数据集合并而不出现截断值,保证了数据库的完整性;通过删除缺失变量和观察、合并重复变量和识别重复观察等过程,最终结合人工识别完成了体检数据预处理,形成了可供研究者进一步使用的健康体检数据库。在处理过程中编写了SAS宏过程,实现了数据预处理代码模块化。结论通过Excel和SAS软件可以实现健康体检数据高效预处理、提高了数据质量、增加了数据可利用性,为数据库的利用和分析奠定基础,为健康体检数据的多中心研究应用的实现提供可能,具有一定的应用推广价值。
Objective To systematically analyze the data characteristics of the current health examination data,and to realize the data preprocessing by using Excel and SAS software macro process.Methods Based on the physical examination data from the physical examination data platform of a municipal tertiary hospital from October 2017 to December 2020,the characteristics of the current physical examination data were summarized through data combing,and the corresponding preprocessing rules were formulated.Based on Excel and SAS software,the specific data preprocessing scheme,operation process and macro code were proposed.data characteristics were summarized through data sorting,preprocessing rules were formulated,and specific solutions,operation procedures and macro codes were proposed based on Excel and SAS software.Results The batch column names of physical examination data were converted by Excel and SAS software,making them conform to the variable name naming rules of SAS software.Multiple data sets with different structures were realized without truncation value,which ensured the integrity of the database.By deleting missing variables and observation,combining duplicate variables and identifying duplicate observation and other processes,the physical examination data was preprocessed in combination with manual identification,and a health examination database for further use by researchers was formed.In the process of processing,the SAS macro process was written to realize the modularization of data preprocessing code.Conclusion Excel and SAS software can be used to efficiently and quickly process health physical examination data,improve data quality,increase data availability,lay a foundation for database utilization and analysis,and provide the possibility for the realization of multi-center research on health physical examination data,so they provide the value of popularize and application.
作者
张丽君
黄艳艳
蒲杨
陈柯
徐凡
罗祥力
石丘玲
Zhang Lijun;Huang Yanyan;Pu Yang;Chen Ke;Xu Fan;Luo Xiangli;Shi Qiuling(School of Public Health,Chongqing Medical University,Chongqing 400016,China;The State Key Laboratory of Ultrasound in Medicine and Engineering,Chongqing Medical University,Chongqing 400016,China;Department of Health Management Center,Nanchong Central Hospital,North Sichuan Medical University,Nanchong 637001,China;Department of Obstetrics and Gynecology,Nanchong Central Hospital,North Sichuan Medical University,Nanchong 637001,China)
出处
《中国医院统计》
2023年第1期64-70,共7页
Chinese Journal of Hospital Statistics
基金
国家自然科学基金面上项目(81872506)
四川省卫生健康委员会医学科技项目(21PJ93)
川北医学院校级科研发展计划(CBY20-QA-Z06)。
关键词
健康体检数据
预处理
数据清洗
SAS软件
health examination data
data preprocessing
data cleaning
SAS software
