北京生物医学工程

基于ｏｐｅｎＥＨＲ的医疗过程数据抽取与转换软件设计实现

Design and implementation of medical process data extraction and transform software based on openEHR

作者：徐海峰毛华坚杨雨李梅赵东升

单位：军事医学研究院科研保障中心（北京 100850）,<br />新疆军区总医院信息科（乌鲁木齐 830000）,<br />国家卒中数据中心（北京 100101）,<br />通信作者：赵东升，研究员。E-mail: dszhao@bmi.ac.cn

关键词： openEHR；AQL；过程挖掘；事件日志；临床数据检索

分类号：R318 

出版年·卷·期（页码）：2022·41·4（390-398）

摘要：

目的随着医疗数据的快速增长，过程挖掘成为一个新的研究热点。然而目前缺乏能够直接用于医疗过程挖掘的数据抽取工具，为此课题组开发了基于openEHR原型查询语言（archetype query language, AQL）的数据抽取软件，支持从兼容openEHR标准的医疗信息系统中提取事件日志，便于临床科研人员进行过程挖掘与分析。方法首先，对openEHR的元数据进行预处理，解析原型（archetype）和模板（template）文件，确定其中每个数据项的对应关系；其次，通过WordNet字典进行查询扩展，得到用户输入的同义词列表；然后，根据用户选择的数据项和设置的检索条件，自动生成原型查询语言脚本；最后，在电子病历服务器上运行AQL脚本提取出所需数据，并转换为过程挖掘所使用的标准事件日志格式（extensible event stream, XES）。结果本文以卒中院内筛查项目为例，将临床研究中3种常用的数据检索类型作为功能指标，对软件功能进行了验证。实验结果表明，在输入查询条件后，软件能够自动生成和执行AQL脚本，并正确返回转换后的日志文件。结论本文开发的软件为临床科研人员提供了一种易用的医疗过程数据获取工具，它能够有效屏蔽异构信息系统的复杂性，便于开展医疗过程挖掘的分析与研究工作。

Objective With the rapid growth of medical data, process mining in healthcare has become a new research hotspot. However, there are few general data extraction methods for process mining in healthcare. Therefore, we developed a data extraction software based on the Archetype Query Language (AQL) of openEHR to extract event logs from medical information systems compatible with openEHR standard, which is convenient for clinical researchers to carry out process mining and analysis. Methods Firstly, the metadata of openEHR is preprocessed, and the Archetype and Template files are parsed to determine the corresponding relationship of each data item. Secondly, query expansion is carried out through WordNet dictionary to get the synonyms of search item entered by users. Then, AQL scripts are automatically generated according to the data items and retrieval conditions selected by users. Finally, the AQL scripts are committed to Electronic Medical Record (EMR) server to extract data required, which are converted into the standard event log format (eXtensible Event Stream, XES) used in process mining. Results We verify the function of this software by taking the stroke registry program as a case study. For three data queries commonly used in clinical research, AQL scripts can be generated and executed by this software to get event logs. Conclusions The software developed in this paper provides an easy-to-use tool for clinical researchers to obtain and format event data. It can effectively avoid the complexity of heterogeneous information systems, facilitating the analysis and research of process mining in healthcare.

参考文献：

[1] van der Aalst WMP. Process mining: data science in action [M]. Berlin: Springer, 2016.
[2] Rojas E, Munoz-Gama J, Sepúlveda M, et al. Process mining in healthcare: a literature review [J]. Journal of Biomedical Informatics, 2016, 61: 224-236.
[3] Mans RS, Schonenberg H, Song M, et al. Application of process mining in healthcare—a case study in a Dutch hospital [J]. Communications in Computer and Information Science, 2008, 25: 425-438.
[4] Kirchner K, Herzberg N, Rogge-Solti A, et al. Embedding conformance checking in a process intelligence system in hospital environments [J]. Process Support and Knowledge Representation in Health Care, 2013, 7738: 126-139.
[5] Kaymak U, Mans R, van de Steeg T, et al. On process mining in health care [C]//2012 IEEE International Conference on Systems, Man, and Cybernetics. Seoul: IEEE, 2012: 1859–1864.
[6] Kalra D, Beale T, Heard S. The openEHR Foundation [J]. Studies in ?Health Technology and Informatics, 2005, 115: 153-173.
[7] de Moraes JLC, de Souza WL, Pires LF, et al. A methodology based on openEHR archetypes and software agents for developing e-health applications reusing legacy systems [J]. Computer Methods and Programs in Biomedicine, 2016, 134: 267-287.
[8] Kohla CD, Gardec S, Knaup P. Facilitating secondary use of medical data by using openEHR archetypes [J]. Studies in Health Technology and Informatics, 2010, 160: 1117-1121.
[9] Frade S, Freire SM, Sundvall E, et al. Survey of openEHR storage implementations [C]// 26th International Symposium on Computer-Based Medical Systems (CBMS). Porto, Portugal: IEEE Press, 2013: 303-307.
[10] Ma C, Frankel H, Beale T, et al. EHR query language (EQL) - a query language for archetype-based health records [J]. Studies in Health Technology and Informatics, 2007,129(Pt 1): 397-401.
[11] Chen R, Klein G. The openEHR Java reference implementation project [J]. Studies in health technology and informatics, 2007, 129(Pt 1): 58-62.
[12] IEEE Standards. IEEE standard for extensible event stream (XES) for achieving interoperability in event logs and event streams [S]// IEEE Standards 1849–2016. NK, USA: IEEE, 2016: 1-50.
[13] Fellbaum C. WordNet: an electronic lexical database [M]. Cambridge, MA: MIT Press, 1998.
[14] Günther CW, Verbeek E. OpenXES developer guide [R]. Eindhoven: ?Technische Universiteit Eindhoven University of Technology, 2014: 1-37.
[15] 《中国脑卒中防治报告》编写组.《中国脑卒中防治报告2019》概要[J].中国脑血管病杂志,2020, 17(5): 272-281.
Report on stroke prevention and treatment in China Writing Group. Brief report on stroke prevention and treatment in China, 2019 [J]. Chinese Journal of cerebrovascular disease, 2020,17 (5): 272-281.
[16] 杨雨, 赵东升, 杨淞淳, 等. 脑卒中筛查数据建模研究[J]. 中国卫生信息管理杂志, 2021, 18(4): 561-566.
Yang Y, Zhao DS, Yang SC, et al. Stroke screening data modeling [J]. Chinese Journal of Health Informatics and Management, 2021, 18(4): 561-566.
[17] Xu HF, Pang JF, Yang X, et al. Using predictive process monitoring to assist thrombolytic therapy decision-making for ischemic stroke patients [J]. BMC Medical Informatics and Decision Making, 2020, 20(Suppl 3): 120.
[18] Xu HF, Pang JF, Yang X, et al. Modeling clinical activities based on multi-perspective declarative process mining with openEHR’s characteristic [J]. BMC Medical Informatics and Decision Making, 2020, 20(Suppl 14): 303.
[19] Yang L, Huang X, Li J. Discovering clinical information models online to promote interoperability of electronic health records: a feasibility study of OpenEHR [J]. Journal of Medical Internet Research, 2019, 21(5): e13504.
[20] Almeida J, Frade S, Cruz-Correia R. Exporting data from an openEHR repository to standard formats [J]. Procedia Technology, 2014, 16: 1391-1396.
[21] Khennou F, Khamlichi YI , Chaoui NEH. Improving the use of big data analytics within electronic health records: a case study based OpenEHR [J]. Procedia Computer Science, 2018, 127: 60-68.
[22] Delussu G, Lianas L, Frexia F, et al. A scalable data access layer to manage structured heterogeneous biomedical data [J]. PLoS One, 2016,11(12): e0168004.
[23] 刘骏健. 基于openEHR的临床数据中心设计与实现 [D]. 杭州：浙江大学, 2016.
Liu JJ. Design and implementation of clinical data repository based on OpenEHR [D]. ?Hangzhou：Zhejiang University, 2016.

服务与反馈：

【文章下载】【加入收藏】

提示：您还未登录，请登录！点此登录