北京生物醫(yī)學(xué)工程

基于ｏｐｅｎＥＨＲ的醫(yī)療過程數(shù)據(jù)抽取與轉(zhuǎn)換軟件設(shè)計(jì)實(shí)現(xiàn)

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

作者：徐海峰毛華堅(jiān) 楊雨李梅趙東升

單位：軍事醫(yī)學(xué)研究院科研保障中心（北京 100850）,<br />新疆軍區(qū)總醫(yī)院信息科（烏魯木齊 830000）,<br />國家卒中數(shù)據(jù)中心（北京 100101）,<br />通信作者：趙東升，研究員。E-mail: [email protected]

關(guān)鍵詞： openEHR；AQL；過程挖掘；事件日志；臨床數(shù)據(jù)檢索

分類號(hào)：R318 

出版年·卷·期（頁碼）：2022·41·4（390-398）

摘要：

目的隨著醫(yī)療數(shù)據(jù)的快速增長，過程挖掘成為一個(gè)新的研究熱點(diǎn)。然而目前缺乏能夠直接用于醫(yī)療過程挖掘的數(shù)據(jù)抽取工具，為此課題組開發(fā)了基于openEHR原型查詢語言（archetype query language, AQL）的數(shù)據(jù)抽取軟件，支持從兼容openEHR標(biāo)準(zhǔn)的醫(yī)療信息系統(tǒng)中提取事件日志，便于臨床科研人員進(jìn)行過程挖掘與分析。方法首先，對(duì)openEHR的元數(shù)據(jù)進(jìn)行預(yù)處理，解析原型（archetype）和模板（template）文件，確定其中每個(gè)數(shù)據(jù)項(xiàng)的對(duì)應(yīng)關(guān)系；其次，通過WordNet字典進(jìn)行查詢擴(kuò)展，得到用戶輸入的同義詞列表；然后，根據(jù)用戶選擇的數(shù)據(jù)項(xiàng)和設(shè)置的檢索條件，自動(dòng)生成原型查詢語言腳本；最后，在電子病歷服務(wù)器上運(yùn)行AQL腳本提取出所需數(shù)據(jù)，并轉(zhuǎn)換為過程挖掘所使用的標(biāo)準(zhǔn)事件日志格式（extensible event stream, XES）。結(jié)果本文以卒中院內(nèi)篩查項(xiàng)目為例，將臨床研究中3種常用的數(shù)據(jù)檢索類型作為功能指標(biāo)，對(duì)軟件功能進(jìn)行了驗(yàn)證。實(shí)驗(yàn)結(jié)果表明，在輸入查詢條件后，軟件能夠自動(dòng)生成和執(zhí)行AQL腳本，并正確返回轉(zhuǎn)換后的日志文件。結(jié)論本文開發(fā)的軟件為臨床科研人員提供了一種易用的醫(yī)療過程數(shù)據(jù)獲取工具，它能夠有效屏蔽異構(gòu)信息系統(tǒng)的復(fù)雜性，便于開展醫(yī)療過程挖掘的分析與研究工作。

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.

參考文獻(xiàn)：

[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] 《中國腦卒中防治報(bào)告》編寫組.《中國腦卒中防治報(bào)告2019》概要[J].中國腦血管病雜志,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] 楊雨, 趙東升, 楊淞淳, 等. 腦卒中篩查數(shù)據(jù)建模研究[J]. 中國衛(wèi)生信息管理雜志, 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] 劉駿健. 基于openEHR的臨床數(shù)據(jù)中心設(shè)計(jì)與實(shí)現(xiàn) [D]. 杭州：浙江大學(xué), 2016.
Liu JJ. Design and implementation of clinical data repository based on OpenEHR [D]. ?Hangzhou：Zhejiang University, 2016.

服務(wù)與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請(qǐng)登錄！點(diǎn)此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频