摘要
随着医药卫生事业的发展,临床过程越来越专业化和精细化。临床过程分析与优化着重在辨识出一连串的临床诊疗活动,通过科学分析方法对这些诊疗活动的流程进行分析与优化。其目标是确保临床诊疗活动的执行能具有一定的水准和精确度,并能得到持续性的改善,使得临床诊疗服务水平不断提高。
临床过程分析与优化技术研究是近年来国内外医学信息学的研究热点。已有的研究成果在应用时存在较大的局限性,主要原因是难以满足临床过程的复杂性和灵活性要求,且缺乏能根据医学知识发展和临床环境变化而持续优化与完善的科学分析方法。为此,本论文通过分析临床过程实践的主要特点,将临床过程实践视为一个包括过程表达、执行、分析和优化等多个阶段的完整生命周期的行为,研究了该生命周期中过程表达、过程推荐、知识检索、资源分配、过程评估和分析等关键技术问题,以此为基础初步建立了临床过程分析与优化技术研究体系,主要包括:
●建立符合患者临床诊疗实践的过程表达方法是临床过程分析与优化的基础。针对临床过程灵活多变、变异频繁发生的特点,本论文提出一种分层次的临床过程表达方法,研究临床诊疗过程不同层次的过程表达模型及实现技术,支持临床过程内容和过程结构的动态调整,提高了临床过程表达的灵活性。
●临床过程执行控制是实现临床过程可靠、有效运行的保证。本论文根据临床环境变化对过程执行控制影响较大的特点,建立了自适应的临床过程执行机制,能够在临床过程实践中,根据患者临床状态的变化,选择和推荐适合患者当前状态的临床诊疗计划,依据循证医学原则分析和保证患者的最佳诊疗预后。
●临床过程注重知识使用的准确性和时效性。这要求能够在临床过程中,可以及时为医护人员的诊断治疗工作提供有效的医学知识。现有的知识检索方法或是不能够满足临床过程实践对知识检索的时间要求,或是检出结果准确率较低,难以满足医护人员的实际需要。本论文提出一种医学知识检索和推荐方法。该方法融合了关键词检索技术和协同过滤技术,能够提高医护人员临床工作中的医学知识检索的时效性,促进临床各专科医护人员之间的协作。
·资源合理分配是临床过程高效执行的重要前提。现有的临床过程资源分配机制比较简单,大多关注于资源的权限管理,很少考虑资源分配对临床过程执行性能的影响。本论文提出了一种基于强化学习的临床过程资源分配方法。在临床过程实践中,该方法通过与临床过程环境的实时交互,学习和推理适合当前临床环境的资源分配最佳策略,并在之后相同或相似的临床环境中使用,提高资源的使用效率,改善临床过程的执行性能。
●临床过程执行时,与诊断治疗行为有关的临床信息和过程信息会被各类医疗信息系统记录并保存在临床数据库中,这些信息表达了患者就诊期间的所有行为记录,能反映临床过程执行时的真实情况,为临床过程的分析和优化提供了必要的数据依据。为次,本论文提出基于过程挖掘技术的临床过程评估和分析方法,通过收集、挖掘和分析临床过程执行信息,构建临床过程模型,开展临床过程执行的一致性检验,为临床过程的评估、分析和优化提供技术支持。
本论文在临床特定专科中有针对性的临床过程表达、过程执行、知识推荐、资源分配、过程挖掘等关键技术开展临床实践评估。结果表明,本论文的研究成果能够合理的表达临床过程模型,有效的推荐适合患者状态的医疗干预,灵活的处理过程变异,分配合适的资源开展临床诊疗活动,及时的为医护人员提供所需要的医学知识,促进医护人员之间的协作,优化临床诊疗活动的执行效率,帮助医护人员分析患者临床诊疗行为,改进与优化临床过程。通过融合以上研究成果,本论文研究和实现了一系列临床过程分析与优化技术,通过与其它临床信息系统和功能模块集成,形成面向大中型医院的完整的临床过程分析与优化信息系统框架。本论文是针对临床过程分析与优化技术研究的有益探索和尝试,为最终形成高效的面向临床过程的医疗信息系统平台奠定良好的技术基础。
Along with the development of medicine and technology, clinical process has become more and more specific and subtle. Clinical process analysis and optimization can help sort out the concept of medical practice that could be covered by scientific approaches, improve patient care services, and bring the best clinical prognosis through the scientific methods.
The research on clinical process analyzing and optimizing technologies is becoming an important focus in clinical engineering and medical informatics domain. However, the characters, such as complexity and flexibility of clinical processes, result in the absence of real progress towards applying advances in information technology in order to analyze and optimize clinical processes. Especially, it lacks the scientific methods aimed at continuous optimization of clinical processes within clinical environmental changes. Considering the challenges above, this thesis introduces a detailed analysis of clinical processes, presents an in-depth study on the key technologies of clinical process analysis and optimization, i.e., process representation, execution control, medical knowledge retrieval and recommenda-tion, resource allocation and process analysis, and builds an initial technology framework of clinical processes analysis and optimization. The main work includes the following:
An appropriate clinical process model is the key issue of the efficiency of clinical process practice. This thesis presents a hierarchical clinical process modeling mech-anism. It exploits the later binding modeling technique to support the content changes and the structure adjustments of clinical processes, and enhances the clinical process modeling flexibility.
In order to guarantee the reliable clinical process execution, this thesis presents an adaptive clinical process execution mechanism, which can recommend appropriate medical interventions within the changes of patient state in clinical processes.
Clinical practice heavily depends on the efficiency of knowledge retrieval and uti- lization. It requires to provide medical knowledge timely and accurately in clinical processes. This thesis proposes a clinical process oriented medical knowledge rec-ommendation mechanism, which can improve the efficiency of medical knowledge retrieval and assist medical staffs'work in clinical processes. The proposed solu-tion is easy to implement and can benefit medical staffs by facilitating collaboration work.
Resource allocation is an integral part of clinical processes. It is widely acknowl-edged as being important for the efficiency of clinical processes. This thesis intro-duces a reinforcement learning based clinical resource allocation mechanism, which can optimize resource allocation and improve clinical process performance.
In clinical practice, information about patient care are regularly recorded in vari-ous medical information systems and stored in clinical databases. Those information express the medical behaviors of clinical processes. This thesis proposes a process mining based clinical process analysis and evaluation mechanism in order to sup-port clinical process (re)design and optimization through the collection, mining and analysis of clinical process execution information.
The efficiency and usability of the proposed approaches is validated by a set of experi-ments in specific clinical departments. The experimental results indicate that the proposed approaches can effectively solve the key challenges of clinical processes, optimize the per-formance of the executions of clinical processes, and improve the quality of patient care. By fusing the proposed research results, a clinical processes analyzing and optimizing tech-nology framework is designed and implemented. The methods and practice can favor the dissemination of clinical process analysis and optimization, and can be beneficial for med-ical staffs, patients and hospital managers.
引文
[1]R. Lenz, M. Reichert. IT support for healthcare processes-premises, challenges, perspectives[J]. Data & Knowledge Engineering,2007,61(1):39-58.
[2]R. Lenz, R. Blaser, M. Beyer, O. Heger, C. Biber, M. BAumlein, M. Schnabel. IT support for clinical pathways-lessons learned[J]. International Journal of Medical Informatics,2007,76(3):S397-S402.
[3]K. Kaiser, C. Akkaya, and S. Miksch. How can information extraction ease formal-izing treatment processes in clinical practice guidelines?:A method and its evalua-tion[J]. Artificial Intelligence in Medicine,2007,39(2):151-163.
[4]J. Fox, A. Alabassi, V. Patkar, T. Rose, E. Black. An ontological approach to mod-elling tasks and goals[J]. Computers in Biology and Medicine,2006,36(7-8):837-856.
[5]T. Cheah. The impact of clinical guidelines and clinical pathways on medical prac-tice:Effectiveness and medico-legal aspects [J]. Ann Acad Med Singapore,1998, 27(4):533-539.
[6]黄惠英.医疗质量保证的国际趋势[J].国外医学,医院管理分册,1999,16(1-5).
[7]张宏雁,董军.临床路径在医院管理中的应用[J].国外医学,医院管理分册,2001,18(98-101).
[8]W. Yang, S. Hwang. A process-mining framework for the detection of healthcare fraud and abuse[J]. Expert Systems with Applications,2006,31(1):56-68.
[9]S. Wakamiya, K. Yamauchi. What are the standard functions of electronic clinical pathways?[J]. International Journal of Medical Informatics,2009,78(8):543-550.
[10]J.I. Westbrook, E.W. Coiera, A.S. Gosling, J. Braithwaite. Critical incidents and journey mapping as techniques to evaluate the impact of online evidence retrieval systems on health care delivery and patient outcomes[J]. International Journal of Medical Informatics,2007,76(2-3):234-245.
[11]H. Campbell, R. Hotchkiss, N. Bradshaw, M. Porteous. Integrated care pathways[J]. British Medical Journal,1998,316(7125):133-137.
[12]D.W. Bates, G.J. Kuperman, S. Wang, T. Gandhi, A. Kittler and L. Volk. Ten com-mandments for effective clinical decision support:making the practice of evidence-based medicine a reality [J]. Journal of the American Medical Informatics Associa-tion,2003,10(6):523-530.
[13]J. Cheah. Development and implementation of a clinical pathway programme in an acute care general hospital in singapore [J]. International Journal for Quality in Health Care,2000,12(5):403-412.
[14]M. Peleg, S. Tu, J. Bury, P. Ciccarese, J. Fox, R.A. Greenes, R. Hall, P.D. John-son, N. Jones, A. Kumar, S. Miksch, S. Quaglini, A. Seyfang, E.H. Shortliffe, M. Stefanelli. Comparing computer-interpretable guideline models:a case-study approach[J]. Journal of the Americian Medical Informatics Association,2003, 10(1):52-68.
[15]Committee on Quality of Health Care in America IOM. Crossing the quality chasm: a new health system for the 21st century [M]. National Academy Press, Washington, DC,2001.
[16]R. Heeks. Health information systems:Failure, success and improvisatoin[J]. Inter-national Journal of Medical Informatics,2006,75(2):125-137.
[17]R. Haux. Health information systems-past, present, future[J]. International Journal of Medical Informatics,2006,75(3-4):268-281.
[18]PL. Reichertz. Hospital information systems-past, present, future[J]. International Journal of Medical Informatics,2006,75(3-4):282-299.
[19]B. Hunter, J. Segrott. Re-mapping client journeys and professional identities:A review of the literature on clinical pathways [J]. International Journal of Nursing Studies,2008,45(4):608-625.
[20]J. van de Klundert, P. Gorissen, S. Zeemering. Measuring clinical pathway adher-ence[J]. Journal of Biomedical Informatics, Available online 7 August 2010.
[21]A.V. Gheorghe, H.N. Bali, W.J. Hill, E.R. Carson. Dynamic decision models for clinical diagnosis[J]. International Journal of Bio-Medical Computing,1976, 7(2):81-92.
[22]D.F. Sittig, A. Wright, J.A. Osheroff, B. Middleton, J.M. Teich, J.S. Ash, E. Camp-bell, D.W. Bates. Grand challenges in clinical decision support[J]. Journal of Biomedical Informatics,2008,41(2):387-392.
[23]D. Isern, A. Moreno. Computer-based execution of clinical guidelines:A review[J]. International Journal of Medical Informatics,2008,77(12):787-808.
[24]Y. Ye, Z. Jiang, X. Diao, D. Yang, G. Du. An ontology-based hierarchical semantic modeling approach to clinical pathway workflows[J]. Computers in Biology and Medicine,2009,39(8):722-732.
[25]T. Benson, R. Page. Electrnoc care pathways:definition of terms[S]. NHS National Programme for IT (discussion paper) Version 1.2.2004.
[26]A.L. Bhasale, G.C. Miller, S.E. Reid, H.C. Britt. Analysing potential harm in australian general practice:an incident-monitoring study[J]. Med. J. Aust.,1998, 169(2):73-76.
[27]T.A. Brennan, L.L. Leape. Adverse events, negligence in hospitalized patients:re-sults from the harvard medical practice study[J]. Perspect. Healthc. Risk Manage., 1991, 11(2):2-8.
[28]T.A. Brennan et al. Incidence of adverse events and negligence in hospitalized pa-tients. results of the harvard medical practice study[J]. N. Engl. J. Med.,1991, 324(6):370-376.
[29]R.M. Wilson, B.T. Harrison, R.W. Gibberd, J.D. Hamilton. An analysis of the causes of adverse events from the quality in australian health care study [J]. Med. J. Aust., 1999,170(9):411-415.
[30]R.M. Wilson, W.B. Runciman, R.W. Gibberd, B.T. Harrison, L. Newby, J.D. Hamil-ton. The quality in australian health care study[J]. Med. J. Aust.,1995,163(9):458-471.
[31]C. Vincent, G. Neale, M. Woloshynowych. Adverse events in british hospitals:pre-liminary retrospective record review[J]. BMJ,2001,322(7285):517-519.
[32]Z. Huang, W.M.R van der Aalst, X. Lu, H. Duan. Reinforcement learning based resource allocation in business process management[J]. Data & Knowledge Engi-neering,2010, accepted.
[33]K. Zheng, R. Padman, M.P. Johnson, H.S. Diamond. Understanding technology adoption in clinical care:Clinician adopotion behavior of a point-of-care reminder system[J]. International Jounral of Medical Informatices,2005,74(7-8):535-543.
[34]M.J. Ball. Hospital information systems:perspectives on problems and prospects, 1979 and 2002[J]. International Journal of Medical Informatics,2003,69(2-3):83-89.
[35]J. Wu, Y. Chen, R.A. Greenes. Healthcare technology management competency and its impacts on IT-healthcare partnerships development[J]. International Journal of Medical Informatics,2009,78(2):71-82.
[36]A.A.T. Bui, D.R. Aberle, and H. Kangarloo. Timeline:Visualizing integrated patient records [J]. IEEE Transactions on Information Technology in Biomedicine,2006, 11(4):462-474.
[37]The DICOM V3.0 Standard[S]. http://www.nema.org. Last access at 2010-9-25,.
[38]Health Level Seven V3.0 Standard[S]. http://www.hl7.org/. Last access at 2010-9-25,.
[39]Integrating the Healthcare Enterprise[S]. http://www.ihe.net/. Last access at 2010-9-25,.
[40]K.N. Lohr, K. Eleazer, J. Mauskopf. Health policy issues and applications for evidence-based medicine and clinical practice guidelines [J]. Health Policy,1998, 46(1):1-19.
[41]M.J. Field, K.N. Lohr. Clinical Practice Guidelines:Directions for a New Pro-gram[S]. Committee to Advise the Public Health Service on Clinical Practice Guide-lines, Institute of Medicine. Washington DC:National Academy Press,1990.
[42]Y. Shahar. Automated support to clinical guidelines and care plans:The intention-oriented view[R]. http://www.openclinical.org/docs/int/briefingpapers/shahar.pdf, 2002.
[43]PL. Elkin, M. Peleg, R. Lacson, et al. Toward standardization of electronic guideline representation[J]. MD Computing,2000,17(6):39-44.
[44]M.K. Ying, S.J. Sadahiro. Charting by variance[J]. Journal of the American Dietetic Association,1996,96(9):A34.
[45]A. Okita, et al. Variance analysis of a clinical pathway of video-assisted single lobectomy for lung cancer[J]. Surgery Today,2009,39(2).
[46]J.T. Davis, H.D. Allen, K. Felver, H.M. Rummell, J.D. Powers, D.M. Cohen. Clin-ical pathways can be based on acuity, not diagnosis[J]. The Annals of Thoracic Surgery,1995,59(5):1074-1078.
[47]马俊.临床路径备要-1[J].中国卫生质量管理,2005,12(1):1-4.
[48]马俊.临床路径备要-2[J].中国卫生质量管理,2005,12(2):1-2.
[49]马俊.临床路径备要-3[J].中国卫生质量管理,2005,12(3):1-4.
[50]R. Fox, S. mORAN, A. MacCormick. Guidance for integrated care pathways:a reference document for an acute NHS trust[J]. Journal of Integrated Care Pathways, 2003,7:100-106.
[51]K. Uzark. Clinical pathways for monitoring and advancing congenital heart disease care[J]. Progress in Pediatric Cardiology,2003,18(2):131-139.
[52]M. Loeb, S.C. Carusone, R. Goeree, S.D. Walter, K. Brazil, P. Krueger, A. Simor, L. Moss, T. Marrie. Effect of a clinical pathway to reduce hospitalizations in nursing home residents with pneumonia[J]. The Journal of the American Medical Associa-tion,2006,295(21):2503-2510.
[53]R.J. Lutterman. The critical path method alone does nothing to improve perfor-mance[J]. Qual. Rev. Bull,1993,5:142.
[54]杜刚,江志斌,刁晓娣,姚阳.基于工作流驱动的手术临床路径建模及系统架构[J].上海交通大学学报,2008,42(5).
[55]J. Leu, Y. Huang. An application of business process method to the clinical effi-ciency of hospital[J]. Journal of Medical Systems,2010, DOI 10.1007s10916-009-9376-4.
[56]L. Fischer. Workflow Handbook 2005[M]. Future Strategies, ISBN 0-9703509-8-8, 2005.
[57]GUIDE[S]. http://www.openclinical.org/gmm_guide.htmll. Last access at 2010-09-25,.
[58]S. Quaglini, M. Stefanelli, A. Cavallini, et al. Guideline-based careflow systems[J]. Artificial Intelligence in Medicine,2000,20(1):5-22.
[59]S. Quaglini, M. Stefanelli, G. Lanzola, et al. Flexible guideline-based patient care-flow systems[J]. Artificial Intelligence in Medicine,2001,22(1):65-80.
[60]Asbru[S]. http://www.openclinical.org/gmm_asbru.html. Last access at 2010-09-25,.
[61]S. Miksch, Y. Shahar, P. Johnson. Asbru:a task-specific, intention-based, and time-oriented language for representing skeletal plans [C]. In Proceeding of the 7th Work-shop on Knowledge Engineering Methods and Languages.1997:9-20.
[62]Arden[S]. http://www.openclinical.org/gmm_ardensyntax.htmll. Last access at 2010-09-25,.
[63]G. Hripcsak, P. Ludemann, T.A. Pryor, et al. Rationale for the arden syntax[J]. Computers and Biomedical Research,1994,27(4):291-324.
[64]PROforma[S]. http://www.openclinical.org/gmm_proforma.html. Last access at 2010-09-25,.
[65]GLIF[S]. http://www.openclinical.org/gmm_glif.htmll. Last access at 2010-09-25,.
[66]D.R. Sutton, J. Fox. The syntax and semantics of the PROforma guideline model-ing language[J]. Journal of the American Medical Informatics Association,2003, 10(5):433-443.
[67]J. Fox, N. Johns, A. Rahmanzadeh. Disseminating medical knowledge:the PRO-forma approach [J]. Artificial Intelligence in Medicine,1998,14(1-2):157-181.
[68]A.A. Boxwala, M. Peleg, S. Tu, et al. GLIF3:a representation format for sharable computer-interpretable clinical practice guidelines [J]. Journal of Biomedical Infor-matics,2004,37(3):147-161.
[69]N. Mulyar, et al. A pattern-based analysis of clinical computer-interpretable guide-line modeling languages [J]. Journal of the American Medical Informatics Associa-tion,2007,14(6):781-787.
[70]D. Wang, M. Peleg, S.W. Tu, et al. Representation of Clinical Practice Guidelines for Computer-Based Implementations[S]. IOS Press.2001.
[71]D. Wang, M. Peleg, S.W. Tu, et al. Representation primitives, process models and patient data in computer-interpretable clinical practice guidelines:A literature re-view of guideline representation models [J]. International Journal of Medical Infor-matics,2002,68(1-3):59-70.
[72]G. Duftschmid, S. Miksch, W. Gall. Verification of temporal scheduling constraints in clinical practice guidelines[J]. Artificial Intelligence in Medicine,2002,25(2):93-121.
[73]B. Perez, I. Porres. Authoring and verification of clinical guidelines:A model driven approach[J]. Journal of Biomedical Informatics,2010,43(4):520-536.
[74]P. Barahona, F. Azevedo, M. Veloso, N. Estevao, R. Gallego. Computerising a guide-line for the management of diabetes[J]. International Journal of Medical Informatics, 2001,64(2-3):275-284.
[75]M. Peleg, S.W. Tu. Design patterns for clinical guidelines[J]. Artificial Intelligence in Medicine,2009,47(1):1-24.
[76]E. Shalom, et al. A quantitative assessment of a methodology for collaborative spec-ification and evaluation of clinical guidelines[J]. Journal of Biomedical Informatics, 2008,41(6):889-903.
[77]J.A.M. Gray. Evidence-based Healthcare:How to Make Health Policy and Manage-ment Decisions Churchill Liveingstone[M]. Edinburgh,1997.
[78]A.M. Cohen, P.Z. Stavri, W.R. Hersh. A categorization and analysis of the criticisms of evidence-based medicine[J]. International Journal of Medical Informatics,2004, 73(1):35-43.
[79]N.A. Black. Developing high-quality clinical databases [J]. British Medical journal, 1997,315(381):831-832.
[80]J.N. Guidi, E.A. Fox. Information retrieval and genomics-an introduction[J]. Com-puters in Biology and Medicine,1996,26(3):179.
[81]G.W. Furnas, T.K. Landauer, L.M. Gomez, S.T. Dumais. The vocabulary problem in human-system communication [J]. Communications of the ACM,1987,30(11):964-971.
[82]P. Srinivasan. Optimal document-indexing vocabulary for medline[J]. Information Processing & Management,1996,32(4):431-443.
[83]G.C. Cimino, S.B. Johnson, P. Peng, A. Aguirre. From icd0-cm to mesh using the umls:A how-to guide[C]. In Proceeding of the Annual Symposium on Computer Applications in Medical Care. vol 41.1994:730-734.
[84]B.T. Bartell, G.W. Cottrell, R.K. Belew. Representing documents using an explicit model of their similarities [J]. Journal of the American Society for Information Scinece,1995,46(4):254-271.
[85]G.C. Chute, Y. Yang, D.A. Evans. Latent semantic indexing of medical diagnoses using umls semantic structures [C]. In Proceeding of the 15th SCAMC, Washington, DC.1991:185-189.
[86]R. Kukafka, J.S. Ancker, C. Chan, J. Chelico, S. Khan, S. Mortoti, K. Natarajan, K. Presley, K. Stephens. Redesigning electronic health record systems to support public health[J]. International Journal of Medical Informatics,2007,40(4):398-409.
[87]K. Smith, D. Kalra. Electronic health records in complementary and alternative medicine[J]. International Journal of Medical Informatics,2008,77(9):576-588.
[88]M. Hagglund, I. Scandurra, S. Koch. Scenarios to capture work processes in shared homecare-from analysis to application [J]. Internation Journal of Medical Informat-ics,2010,79(6):e116-e125.
[89]S.C. Kim, I. Horowitz, K.K. Young, T.A. Buckley. Flexible bed allocation and per-formance in the intensive care unit[J]. Journal of Operations Management,2000, 18(4):427-443.
[90]C.D. Spyropoulos. AI planning and scheduling in the medical hospital environ-ment[J]. Artificial Intelligence in Medicine,2000,20(2):101-111.
[91]A. Oddi, A. Cesta. Toward interactive scheduling systems for managing medical resources[J]. Artificial Intelligence in Medicine,2000,20(2):113-138.
[92]I.B. Vermeulen, S.M. Bohte, S.G. Elkhuizen, et al. Adaptive resource allocation for efficient patient scheduling [J]. Artificial Intelligence in Medicine,2009,46(1):67-80.
[93]D.F. Ferraiolo, R. Sandhu, S.Gavrila, D.R. Kuhn and R. Chandramouli. Proposed NIST standard for role-based access control[J]. ACM Transactions on Information and System Security,2001,4(3):224-274.
[94]Z. Xiangpeng, A. Cerone, P. Krishnan. Verifying B PEL workflows under autho-rization constraints [C]. In SHETH S D J F A. Proceeding of the 4th International Business Process Management conference, BPM2006. vol 4102.2006:439-444.
[95]C. Wolter, A. Schadd. Modeling of task-based authorization constraints in BPMN[C]. In ROSEMANN G A P D M. Proceeding of the 5th International Busi-ness Process Management conference, BPM2007. vol 4714.2007:64-79.
[96]A. Kumar, W.M.P. van der Aaslt and E.M.W. Verbeek. Dynamic work distribution in workflow management systems:How to balance quality and performance [J]. Journal of Management Information Systems,2002,18(3):157-193.
[97]W. Pesic, W.M.P. van der Aalst. Modeling work distribution mechanisms using col-ored petri nets[J]. International Journal of Software Tools for Technology Transfer, 2007,9(3-4):327-352.
[98]Staffware, plc, Berkshire. Using the Staffware Process Clinet[S].2002.
[99]FileNet Corporation, Costa, Mesa. FileNet Business Process Manager 3.0[S].2004.
[100]Pallas Athena BV, Apeldoorn. FLOWer User Manual[S].2002.
[101]R. Agrawal, D. Gunopulos, F. Leymann. Mining process models from workflow logs[C]. In Proceeding of the 6th International Conference on Extending Database Technology.1998:469-483.
[102]J.E. Cook, A.L. Wolf. Discovering models of software process fromevent-based data[J]. ACM Transaction on Sofware Engineering and Methodology,1998, 7(3):215-249.
[103]W.M.P. van der Aalst, A.J.M.M. Weijters and L. Maruster. Workflow Min-ing:discovering process models from event logs[J]. IEEE Transactions on Knowl-edge and Data Engineering,2004,16(9):1128-1142.
[104]M. Miller, N. Kearney. Guidelines for clinical practice:development, dissemination and implementation [J]. International Journal of Nursing Studies,2004,41(7):813-821.
[105] L. Ohno-Machado, J.H. Cennari, S.N. Murphy, et al. The guideline interchange format: A model for representing guidelines [JJ. Journal of the American Medical Informatics Association, 1998, 5(4):357-372.
[106] B.M. Reilly. The essence of ebm[J]. BMJ, 2004, 329(7473):991-992.
[107] S.W. Tu, M.A. Musen. A flexible approach to guideline modeling[C]. In AMIA Symposium. 1999.
[108] S.W. Tu, M.A. Musen. From guideline modeling to guideline execution: defining guideline-based decision-support services[C]. In AMIA Symposium. 2000.
[109] I.N. Purves, B. Sugden, N. Booth, M. Sowerby. The PRODIGY project - the iterative developement of the releaseone model[C]. In AMIA Symposium. 1999.
[110] K.P. Adlassnig, C. Combi, A.K. Das, E.T. Keravnou, G. Pozzi. Temporal represen-tation and reasoning in medicine: research directions and challenges[J]. Artificial Intelligence in Medicine, 2006,38(2): 101-13.
[111]朱士俊,鲍玉荣,刘爱民,刘海一,罗艳侠,闰宇翔,常文虎,张迎媛,鲁盛康,刘俊田,张正华.北京地区医院按drgs付费和临床路径应用研究[J].中华医院管理杂志,2008,24(3).
[112] J. Tan, A. Foo, D. Cheong. Colorectal clinical pathways: A method of improving clinical outcome?[J]. Asian Journal of Surgery, 2005, 28(4):252-256.
[113]何雨生,孙宏宇.计算机化临床实践指南研究进展[J].中国数字医学,2070,2(l).
[114]李毅,赵军平,李书章.计算机化临床实践指南的研究和实现[J].中国医疗器械,2009,33(6).
[115] I. Bichindaritz. Case-based reasoning in the health sciences[J]. Artificial Intelli- gence in Medicine, 2006,36(2): 121-125.
[116] H. Schonenberg, et al. Supporting flexible processes through recommendations based on history[C]. In Proceeding of the 6th International Business Process Man- gement conference, vol 5240. 2008.
[117]W.M.P. van der Aalst. Tomtom for business process management[C]. In Lecture Notes in Computer Science, vol 5565.2009.
[118]M. Reichert, S. Rinderle, P. Dadam. Adept workflow management system:flexible support for enterprise-wide business processes[C]. In Proceeding of the 1st Interna-tional Conference on Business Process Management.2003:370-379.
[119]Z. Pawlak. Rough sets[J]. International Journal of Parallel Programming,1982, 11(5):341-356.
[120]Z. Pawlak. Rough sets and intelligent data analysis [J]. Information Sciences,2002, 147(1-4):1-12.
[121]Z. Pawlak, A. Skowron. Rough sets:Some extensions [J]. Information Sciences, 2007,177(1):28-40.
[122]Z. Pawlak, A. Skowron. Rudiments of rough sets [J]. Information Sciences,2007, 177(1):3-27.
[123]I. Bichindaritz, E. Kansu, K.M. Sullivan. Case-based reasoning in CARE-PARTNER:gathering evidence for evidence-based medical practice[C]. In Proceed-ing of the 4th European Workshop on Advances in Case-Based Reasoning.1998: 334-345.
[124]A. Aamodt, E. Plaza. Case-based reasoning:Foundational issues, methodological variations, and system approaches [J]. AI communications,1994,7(1):39-59.
[125]D. Leake. Case-Based Reasoning:Experiences, Lessons, and Future directions[M]. AAAI Press, Menlo Park, CA,1996.
[126]Q. Hu, D. Yu, J. Liu, C. Wu. Neighborhood rough set based heterogeneous feature subset selection [J]. Information Sciences,2008,178(18):3577-3594.
[127]F. Lin, S. Chou, S. Pan, Y. Chen. Mining time dependency patterns in clinical path-ways[J]. International Journal of Medical Informatics,2001,62(1):11-25.
[128]V. Sintchenko, J.R. Iredell, G.L. Gilbert, E. Coiera. Handheld computer-based de-cision support reduces patient length of stay and antibiotic prescribing in critical care[J]. Journal of the American Medical Informatics Association,2005,12(4):398-402.
[129]S. Montani, R. Bellazzi. Supporting decisions in medical applications:the knowl-edge management perspective[J]. International Journal of Medical Informatics, 2002,68(1-3):79-90.
[130]J.M. Juarez, T. Riestra, M. Campos, A. Morales, J. Palma, R. Marin. Medical knowl-edge management for specific hospital departments [J]. Expert Systems with Appli-cations,2009,36(10):12214-12224.
[131]N. Creswick, J.I. Westbrook. Social network analysis of medication advice-seeking interactions among staff in an australian hospital [J]. International Journal of Medical Informatics, doi:10.1016/j.ijmedinf.2008.08.005.
[132]A. Crabtree. Talking work:language-games, organisations and computer supported cooperative work[J]. Computer Support Cooperative Work,2000,9(2):215-237.
[133]G. Hardstone, M. Hartswood, R. Procter, R. Slack, A. Voss and G. Rees. Supporting informality:team working and integrated care records [C]. In Proceeding of the 2004 ACM Conference on Computer Supported Cooperative Work 2004 Chicago, Illinois, USA.2004.
[134]A.B. Can, N. Baykal. Medicoport:A medical search engine for all[J]. Computer Methods and Programs in Biomedicine,2007,86(1):73-86.
[135]F. Alonso, J.P. Caraca-Valente, A.L. Gonzalez, C. Montes. Combining expert knowl-edge and data mining in a medical diagnosis domain[J]. Expert Systems with Ap-plications,2002,23(4):367-375.
[136]D.F. Sittig, A. Wright, L. Simonaitis, J.D. Carpenter, G.O. Allen, B.N. Doebbeling, A.M. Sirajuddin, J.S. Ash, B. Middleton. The state of the art in clinical manage-ment:An inventory of tools and techniques [J]. International Journal of Medical Informatics,2010,79(1):44-57.
[137]M.J. O'Connor, R.D. Shankar, D.B. Parrish, A.K. Das. Knowledge-data integration for temporal reasoning in clinical trial system[J]. International Journal of Medical Informatics,2009,78(1):S77-S85.
[138]D. Goldberg, D. Nichols, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM,1992,35(12):61-70.
[139]G. Adomavicius, A. Tuzhilin. Multidimensional recommender systems:A data warehousing approach[C]. In WILHELM L F G M U. Proceeding of WELCOM 2001. vol 2232.2001.
[140]K. Honda, H. lchihashi. Component-wise robust linear fuzzy clustering for col-laborative filtering [J]. International Jounral of Approximate Reasoning,2004, 37(2):127-144.
[141]G. Adomavicius, A. Tuzhilin. Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering,2005,17(6):734-749.
[142]G. Salton. Automatic Text Processing[M]. Addison-Wesley Publishing, Reading, MA,1989.
[143]G. Salton, C. Buckley. Improving retrieval performance by relevance feedback[J]. Journal of the American Society for Information Science,1990,41(4):288-297.
[144]P. Ganesan. Exploiting hierarchical domain structure to compute similarity [J]. ACM Transactions on Information System,2003,21(1):64-93.
[145]M. Rodriguuez, M. Egenhofer. Determining semantic similarity among entity classes from different ontologies [J]. IEEE Transactions on Knowledge and Data Engineering,2003,15(2):442-456.
[146]O. Bodenreider. The unified medical language system (umls):integrating biomedi-cal terminology [J]. Nucleic Acids Res,2004, 1(32):D267-D270.
[147]K.E. Campbell, D.E. Oliver and E.H. Shortliffe. The unified medical language sys-tem:toward a collaborative approach for solving terminologic problems[J]. Journal of the American Medical Informatics Association,1998,5(1):12-16.
[148]P. Resnick, N. Iacovou, M. Suchak, et al. Grouplens:an open architecture for col-laborative filtering of netnews[C]. In Proceeding of CSCW'94.1994:175-186.
[149]J. Breese, D. Hecherman, C. Kadie. Empirical analysis of predictive algorithms for collaborative filtering[C]. In Proceeding of UAI'98.1998:43-52.
[150]B. Arwar, G. Karypls, J. Konstan, et al. Item-based collaborative filtering recom-mendation algorithms[C]. In Proceeding of WWW'2001.2001:285-295.
[151]B.M. Kim, Q. Li, et al. A new approach for combining content-based and collabo-rative filters[J]. Journal of Intelligent Information System,2006,27(1):79-91.
[152]G. Karypis. Evaluation of item-based top-n recommendation algorithms[C]. In Pro-ceeding of CIKM'2001.2001:247-254.
[153]B. Arwar, G. Karypis, et al. Analysis of recommendation algorithms for e-commerce[C]. In Proceeding of the 2nd ACM Conference on Electronic Commerce. 2000:158-167.
[154]J. Wang, A.P. de Vries, and MJ.T. Reinders. Unifying user-based and item-based collaborative filtering approaches by similarity fusion[C]. In Proceeding of SI-GIR'06.2006:501-508.
[155]C. Ziegler, J. Golbeck. Investigating interactions of trust and interest similarity [J]. Decision Support Systems,2007,43(2):460-475.
[156]M. Balabanovic, Y. Shoham. Fab:Content-based, collaborative recommendation [J]. Communications of the ACM,1997,40(3):66-72.
[157]G.G. van Merode, S. Groothuis, A. Hasman. Enterprise resource planning for hos-pital[J]. International Journal of Medical Informatics,2004,73(6):493-501.
[158]L. Delorme, J. Rousseau. Memra:An equilibrium model for resource allocation in a health care system[J]. European Journal of Operational Research,1987,29(2):144-158.
[159]N. Ressell, A.H.M. ter Hofstede, D. Edmond, W.M.P. van der Aalst. Workflow resource patterns[R]. Eindhoven University of Technology, Eindhoven,2005.
[160]Y. Liu, J. Wang, Y. Yang and J. Sun. A semi-automatic approach for workflow staff assignment[J]. Computers in Industry,2008,59(5):465-476.
[161]K.R. Baker. Introduction to sequencing and scheduling[M]. Wiley, New York,1974.
[162]K.M. van Hee and J. Wessels. Markov decision processes and strongly excessive functions[J]. Stochastic Processes and their Applications,1978,8(1):59-76.
[163]R.S. Sutton and A.G. Barto. Reinforcement Learning:An Introduction[M]. The MIT Press, Cambridge, MA,1999.
[164]N. Meuleau et al. Solving very large weakly coupled markov decision processes[C]. In AAAI/IAAI.1998.
[165]S.E. Elmagrhraby. Resource allocation via dynamic programming in activity net-works [J]. European Journal of Operational Research,1993,64(2):199-215.
[166]T. Ibaraki, Y. Nakamura. A dynamic programming method for single machine scheduling[J]. European Journal of Operational Research,1994,76(1):72-82.
[167]S. Mahadevan and L.P. Kaelbling. The NSF Workshop on Reinforcement Learning: Summary and Observations[M]. AI Magazine Winter,1996.
[168]C.J.C.H Watkins and P.Dayan. Q-learning[J]. Machine Learning,1992,8(3-4):279-292.
[169]K.H. Quah, C. Quek. Maximum reward reinforcement learning:A non-cumulative reward criterion[J]. Expert System with Applicatoins,2006,31(2):351-359.
[170]G. Tesauro, R. Das, W.E. Walsh, and J.Q. Kephart. Utility-function-driven resource allocation in autonomic systems[C]. In Proceedings of the 2nd IEEE International Conference on Autonomic Computing.2005.
[171]W. Zhang, T. Dietterich. A reinforcement learning approach to job-shop schedul-ing[C]. In Proceeding of IJCAI.1995.
[172]D. Vengerov. A reinforcement learning approach to dynamic resource allocation[J]. Engineering Applications of Artificial Intelligence,2007,20(3):383-390.
[173]W.M.P. van der Aalst, A. Kumar. A reference model for team-enabled workflow management systems[J]. Data & Knolwedge Engineering,2001,38(3):335-363.
[174]S. Rinderle and W.M.P. van der Aalst. Life-cycle support for staff assignement rules in process-aware information systems[R]. TU Eindhoven,2007.
[175]M. Puterman. Markov Decision Processes:Discrete Stochastic Dynamic Program-ming[M]. New York:John Wiley & Sons,2005.
[176]G. Strang. Linear Algebraand its Applications[M]. Academic Press, Orlando, FL, 1980.
[177]P. Stone and M. Veloso. Team-partitioned, opaque-transition reinforecement learn-ing [C]. In Proceeding of the 3rd International Conference on Autonomous Agents. 1999.
[178]张金艳.基于工作流的医疗信息系统研究[D].博士学位论文.浙江大学,2009.
[179]J. Zhang, X. Lu, H. Nie, Z. Huang and W.M.P. van der Aalst. Radiology information system:a workflow-based approach[J]. International Journal of Computer Assisted Radiology and Surgery,2009,4(5):509-516.
[180]W.M.P. van der Aalst. The application of Petri Nets to workflow management[J]. J.Circuit.Syst.Comput,1998,8(1):21-66.
[181]W.M.P. van der Aalst and A.J.M.M. Weijters. Process mining:A research agenda[J]. Computers in Industry,2004,53(3):231-244.
[182]J. Herbst, D. Karagiannis. Workflow mining with inwolve[J]. Computers in Industry, 2004,53(3):245-264.
[183]G. Schimm. Mining exact models of concurrent workflows[J]. Computers in Indus-try,2004,53(3):265-281.
[184]C. Chen and K. Chen and C.Y. Hsu and Y.C. (Jack) Li. Devel-oping guideline-based decision support systems using protege and jess[J]. Computer Methods and Programs in Biomedicine,2010, In Press, Cor-rected Proof:-. http://www.sciencedirect.com/science/article/B6T5J-50F367H-1/2/d7b8930b971d45a897fa2d5ea50d08e6.
[185]T.M.Mitchell. Machine Learning[M]. McGraw-Hill,1997.
[186]P.N. Tan, M. Steinbach, V. Kumar. Introduction to Data Mining[M]. Addison-Wesley,2005.
[187]J.R. Quinlan. C4.5:Programs for Machine Learning[M]. Morgan Kaufmann,1993.
[188]W.M.P. van der Aalst, A.H.M. ter Hofstede. YAWL yet another workflow lan-guage [J]. Information Systems,2005,30(4):245-275.
[189]WfMC. The Workflow Reference Model, Doc. No. TC00-1003[S]. http://www.wfmc.org/,.
[190]C. Tseng, C. Lin, S. Huang, K. Lin, S. Chang, S. Chien. Computer-aided monitoring of surgical pathology workflow[J]. Tzu Chi Medical journal,2009,21(2):140-146.
[191]WfMC. Workflow Management Coalition Audit Data Specification Doc. No. TC-1015[S]. http://www.wfmc.org/,.
[192]W.M.P. van der Aalst, B.F. van Dongen, et al. Workflow mining A survey of issues and approaches[J]. Data & Knowledge Engineering,2003,47(2):237-265.
[193]A.K.A. Medeiros. Genetic Process Mining[D]. PhD thesis. Technology University Eindhoven,2006.
[194]D. Ferreira, M. Zacarias, M. Malheiros and P. Ferreira. Aproaching process mining with sequence clustering:Experiments and findings[C]. In Proceeding of the 5th Business Process Management Conference.2007.