医院麻醉信息系统数据科研化预处理方法探索

doi:10.3969/j.issn.1006-5253.2024.03.013

摘要
图/表
参考文献
相关文章 (1)

全文: PDF (7103 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要目的准确、规范的数据是得出可靠研究结果的基础。本文以肺部手术为例，分析麻醉信息系统的数据特征，并进行清洗、转换、集成和归约等预处理，构建可用于科研分析的数据集。方法收集四川省某肿瘤医院2021年4月至2022年11月行肺部手术患者麻醉信息系统的相关数据。分析源数据特征，并基于Python和SAS软件提出数据预处理流程和宏代码。通过Python的SPLIT语句，SAS宏和函数将文本数据转换为易于数据挖掘的数值数据；通过数据清洗和维归约，填补缺失值、纠正异常和不一致的数据，去除冗余数据；通过NOUNIQUEKEY、SQL和LAG语句实现数据集成，扩大数据体量。结果从麻醉信息系统和医院信息系统中导出2个Excel表，共计1 835条麻醉记录和46 612条医嘱记录。源数据分析发现麻醉信息系统存在医疗术语不规范、语义表达多样性、同一药物多种量纲、部分药物带有后缀“备用”的特点。基于上述数据特点和半结构化的数据结构，编译了3个宏（macro），清洗核查全部药物名称、规范化医疗术语以及统一量纲，最终提取麻醉前、术中和镇痛泵的药物各12、24、12种；完成缺失数据的二次补充，平滑噪声和清理不一致数据；剔除了48条（2.62%）非肺手术的麻醉记录，去除与挖掘任务无关的10个字段；经过数据集成，1 748（97.82%）例麻醉数据与医嘱数据相匹配。通过上述数据预处理流程，最终结构化的数据集中共有1 748例患者，99个变量。结论通过对源数据的分析，制定特异的麻醉数据预处理流程，进而得到了规范、准确的麻醉用药数据。为其他机构麻醉信息的数据科研化提供了方法学参考，同时为需要利用高质量麻醉用药数据的研究提供了可靠的数据基础。

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	向茹梅
	魏星
	戴维
	张丽君
	徐玮
	田杰
	张宏伟
	孙佳昕
	石丘玲

关键词 ：麻醉信息系统, 预处理, 数据清洗, 数据结构化, SAS软件

Abstract：Objective Accurate and standardised data form the foundation for reliable research findings. Taking lung surgery as a case study, we analyse the data traits of an anesthesia information system and undertake preprocessing such as encompassing cleaning, conversion, integration and imputation to build a researchready dataset.Methods Relevant data from the anesthesia information system of patients undergoing lung surgery at Sichuan Cancer Hospital between April 2021 and November 2022 were collected. The characteristics of the source data were analysed, and the Python and SAS software were proposed for data preprocessing. Text data were transformed into numerical values for the ease of data mining using Python's SPLIT statements, SAS macros, and functions. Missing values were filled, and anomalies, inconsistencies, and redundant data were corrected through data cleaning and data reduction. Data integration was achieved through NOUNIQUEKEY, SQL and LAG statements to expand the data volume.Results Two Excel sheets were extracted from the anaesthesia information system and the hospital information system, comprising a total of 1 835 anesthesia records and 46 612 medical records. Analysis of the source data revealed that the anaesthesia information system had idiosyncratic medical lexicon, varied semantic expressions, multiple outlines for identical drugs, and certain drugs ending in "alternate". Based on the given data characteristics and semi-structured data structure, we compiled three macros to clean and validate all drug names, standardise medical terminology, and unify outlines. This process led to the extraction of 12 drugs for pre-anaesthesia, 24 drugs for intraoperative use, and 12 drugs for analgesic pumps. Secondary completion of missing data was performed, as well as noise reduction and cleaning of inconsistent data. Forty-eight anesthesia records (2.62%) of non-pulmonary were excluded and 10 irrelevant fields for the mining task were removed. After data integration, 1 748 cases of anesthesia data (97.82%) were matched with medical prescription data. After the data preprocessing described above, the final structured dataset consisted of 1 748 patients and 99 variables.Conclusion The anaesthesia data preprocessing process developed through the analysis of source data achieves data cleaning, data integration, data transformation and data reduction, and thus obtains standardised and precise drugs data. It provides a methodological reference for data cleaning and structuring of anaesthesia information in other institutions and at the same time provides a reliable data base for research that needs to use high quality anaesthesia medication data, which will contribute to the depth and advancement of related research.

Key words： anesthesia information management system data preprocessing data cleaning data structuring SAS software

收稿日期: 2023-11-22

基金资助:国家重点研发计划“政府间国际科技创新合作”重点专项项目（2022YFE0133100）；
希思科领航肿瘤研究基金项目（Y-2019AZMS-0486）

通讯作者: 石丘玲，Email: qshi@cqmu.edu.cn

引用本文:

向茹梅，魏星，戴维，张丽君，徐玮，田杰，张宏伟，孙佳昕，石丘玲. 医院麻醉信息系统数据科研化预处理方法探索[J]. 中国医院统计, 2024, 31(3): 219-229.
Xiang Rumei，Wei Xing， Dai Wei，Zhang Lijun，Xu Wei，Tian Jie，Zhang Hongwei， Sun Jiaxin，Shi Qiuling. Exploration of pre-processing methods for scientific research of data in hospital anesthesia information management system. journal1, 2024, 31(3): 219-229.

链接本文:

http://manu58.magtech.com.cn/Jwk_zgyytj/CN/10.3969/j.issn.1006-5253.2024.03.013 或 http://manu58.magtech.com.cn/Jwk_zgyytj/CN/Y2024/V31/I3/219

［1］姬娜．医院手术麻醉信息系统的构建与实施［J］．中国医疗设备，2014，29(10)：74-76．DOI: 10.3969/j.issn.1674-1633.2014.10.024.

［2］SIMPAO A F, REHMAN M A. Anesthesia information management systems［J］. Anesth Analg, 2018,127(1):90-94. DOI: 10.1213/ANE.0000000000002545.

［3］SANDBERG W S, SANDBERG E H, SEIM A R, et al. Real-time checking of electronic anesthesia records for documentation errors and automatically text messaging clinicians improves quality of documentation［J］. Anesth Analg, 2008,106(1):192-201, tableofcontents. DOI: 10.1213/01.ane.0000289640.38523.bc.

［4］FRANK S M, SAVAGE W J, ROTHSCHILD J A, et al. Variability in blood and blood component utilization as assessed by an anesthesia information management system［J］. Anesthesiology, 2012,117(1):99-106. DOI: 10.1097/ALN.0b013e318255e550.

［5］NAIR B G, GABEL E, HOFER I, et al. Intraoperative clinical decision support for anesthesia: A narrative review of available systems［J］. Anesth Analg, 2017,124(2):603-617. DOI: 10.1213/ANE.0000000000001636.

［6］黄正东，徐小伟，郭雪清，等．临床麻醉信息系统的建设与应用［J］．中国医疗设备，2009，24(1)：63-64．DOI: 10.3969/j.issn.1674-1633.2009.01.025.

［7］郝晓玲，刘江，马莉．基于护理全程模块化设计的手术麻醉信息系统的应用［J］．中国药物与临床，2019，19(12)：2097-2099．DOI: 10.11655/zgywylc2019.12.072.

［8］李立，周鑫．手术麻醉信息系统应用［J］．现代仪器与医疗，2015，21(3)：25-26．DOI: 10.11876/mimt201503009.

［9］许卫东．手术麻醉信息系统的医疗数据挖掘与分析［D］．重庆：重庆大学，2021．

［10］SUN W C, CAI Z P, LI Y Y, et al. Data processing and text mining technologies on electronic medical records: A review［J］. J Healthc Eng, 2018,2018:4302425. DOI: 10.1155/2018/4302425.

［11］WANG R Y, STOREY V C, FIRTH C P. A framework for analysis of data quality research［J］. IEEE Trans Knowl Data Eng, 1995,7(4):623-640. DOI: 10.1109/69.404034.

［12］宋晓红，张立朝，禄丰年，等．地理国情普查中多源异构数据整合研究［J］．测绘通报，2014(9)：104-107．DOI: 10.13474/j.cnki.11-2246.2014.0307.

［13］庄军，郭平，周杨，等．电子病历数据预处理技术［J］．计算机科学，2007，34(3)：141-144．DOI: 10.3969/j.issn.1002-137X.2007.03.037.

［14］陈霞，邱桃荣，魏玲玲，等．基于数据挖掘的病历数据预处理［J］．计算机与现代化，2007(5)：23-24．DOI: 10.3969/j.issn.1006-2475.2007.05.007.

［15］林予松，王培培，刘炜，等．医疗体检数据预处理方法研究［J］．计算机应用研究，2017，34(4)：1089-1092．DOI: 10.3969/j.issn.1001-3695.2017.04.030.

［16］赵天易，雒琳，何丽云，等．多源异构数据整合在中医药真实世界临床研究中的应用及展望［J］．世界中医药，2022，17(5)：614-619．DOI: 10.3969/j.issn.1673-7202.2022.05.004.

［17］MALLEY B, RAMAZZOTTI D, WU J T Y. Data pre-processing［M］// Secondary Analysis of Electronic Health Records. Cham: Springer, 2016:115-141.10.1007/978-3-319-43742-2_12.

［18］GRANDI F, CAROLI J, ROMANO O, et al. popsicleR: A R package for pre-processing and quality control analysis of single cell RNA-seq data［J］. J Mol Biol, 2022,434(11):167560. DOI: 10.1016/j.jmb.2022.167560.

［19］向穷，施树良，李钰．常用统计软件在生物统计中的应用比较［J］．现代生物医学进展，2009，9(9)：1775-1777．

［20］RIQUELME G, ZABALEGUI N, MARCHI P, et al. A python-based pipeline for preprocessing LC-MS data for untargeted metabolomics workflows［J］. Metabolites, 2020,10(10):416. DOI: 10.3390/metabo10100416.

［21］DEMBE A E, PARTRIDGE J S, GEIST L C. Statistical software applications used in health services research: Analysis of published studies in the U.S［J］. BMC Health Serv Res, 2011,11:252. DOI: 10.1186/1472-6963-11-252.

［22］LAMER A, JEANNE M, VALLET B, et al. Development of an anesthesia data warehouse: Preliminary results［J］. IRBM, 2013,34(6):376-378. DOI: 10.1016/j.irbm.2013.09.005.

［23］LAMER A, ABOU-ARAB O, BOURGEOIS A, et al. Transforming anesthesia data into the observational medical outcomes partnership common data model: Development and usability study［J］. J Med Internet Res, 2021,23(10):e29259. DOI: 10.2196/29259.

［24］LAMER A, DE JONCKHEERE J, MARCILLY R, et al. A substitution method to improve completeness of events documentation in anesthesia records［J］. J Clin Monit Comput, 2015,29(6):741-747. DOI: 10.1007/s10877-015-9661-3.

［25］LAMER A, JEANNE M, MARCILLY R, et al. Methodology to automatically detect abnormal values of vital parameters in anesthesia time-series: Proposal for an adaptable algorithm［J］. Comput Methods Programs Biomed, 2016,129:160-171. DOI: 10.1016/j.cmpb.2016.01.004.

［26］陆丽娜，杨怡玲，管旭东，等．Web日志挖掘中的数据预处理的研究［J］．计算机工程，2000，26(4)：66-67．DOI: 10.3969/j.issn.1000-3428.2000.04.028.

［27］张丽君，黄艳艳，蒲杨，等．基于SAS软件的地市级医院健康体检数据预处理方法探索［J］．中国医院统计，2023，30(1)：64-70．DOI: 10.3969/j.issn.1006-5253.2023.01.013.

［28］刘明吉，王秀峰，黄亚楼．数据挖掘中的数据预处理［J］．计算机科学，2000，27(4)：54-57．DOI: 10.3969/j.issn.1002-137X.2000.04.015.

［29］SAJJADNIA Z, KHAYAMI R, MOOSAVI M R. Preprocessing breast cancer data to improve the data quality, diagnosis procedure, and medical care services［J］.Cancer Inform,2020,19:1176935120917955.DOI:10.1177/1176935120917955.

［30］HAN J W, JIAN P, KAMBER M. Data Mining: Concepts and Techniques［M］. Elsevier Science, 2011.

［31］刘莉，徐玉生，马志新．数据挖掘中数据预处理技术综述［J］．甘肃科学学报，2003，15(1)：117-119．DOI: 10.3969/j.issn.1004-0366.2003.01.027.

［32］ZHENG Y. Methodologies for cross-domain data fusion: An overview［J］. IEEE Trans Big Data, 2015,1(1):16-34. DOI: 10.1109/TBDATA.2015.2465959.

［33］裴丽坚，赵晶，王怡，等．便于交流利于监管：《麻醉记录单标准》解读［J］．中国卫生标准管理，2011，2(4)：19-21．

［34］王德征，江国虹，徐忠良，等．SAS宏程序在病例交叉设计资料整理中的应用［J］．中华疾病控制杂志，2015，19(10)：1057-1061．DOI: 10.16462/j.cnki.zhjbkz.2015.10.021.

［35］KAVELAARS X M, VAN GINKEL J R, VAN BUUREN S. Multiple imputation in data that grow over time: A comparison of three strategies［J］. Multivar Behav Res, 2022,57(2-3):513-523. DOI: 10.1080/00273171.2021.1912582.