基于本体的医学案例库模型研究
|
摘要
目前,在医学领域,医学案例库是极具价值的医学信息仓库,而电子病历正是医学案例库的信息来源,并已得到了广泛的实际应用。但现在的医学案例库中的案例大多是以文本数据的形式存储,计算机无法处理其内涵的语义信息,难以实现自动化的知识获取。此外,由于尚没有标准化的数据格式,不同医学信息系统之间无法实现有效的信息共享和互操作。以上问题必须从形式语义的角度去解决。
本文通过对一体化医学语言系统、Ontology(本体论)、对象数据库等技术的研究,提出基于本体的医学案例库模型。该模型能够在语义层次上描述和存储医学信息,并能实现异构医学案例库之间的信息互操作。具体的研究内容有:
1.文中提出了案例库模型的构建思想和基本结构。该模型是由本体驱动,包括应用层、语义层和数据层三层结构,其中数据层中的医学本体库和对象数据库是整个模型的基础与核心。
2.文中在医学本体库的构建中提出了一种混合策略,即是由全局本体库(概念词典)和局部本体库共同构建医学本体库。以这种策略构建的医学本体库,具有统一的本体基础(概念词典),从而使得异构案例库之间的信息数据互操作成为可能,并在一定程度上提高了医学信息检索的有效性和准确率。
3.模型中采用的对象数据库是一种能够有效表达数据语义信息的数据库模式,通过将本体的方法引入对象数据库模型的定义过程中,以此增强数据库模型的语义表达能力,同时又简化了语义冲突的化解过程,这在一定程度上提高医学信息的存储效率和复用率。
4.文中在对本体映射的研究中,结合本文的模型特点,提出了一种概念相似度计算算法,并对算法的有效性进行了实验验证。该算法能够有效的确定异构本体之间的概念相似程度,为异构医学信息系统之间的本体映射提供了算法支持。以上的研究具有一定的理论价值和实际意义。
Currently, in the medical field, the case is extremely valuable source of knowledge, electronic medical informatics case is the realization of goals, and has been a practical application. But now the case of electronic data is in the form of text, its semantic content of computer information can not handle, and will be difficult to achieve automated knowledge acquisition. Moreover, as the electronic case is still not standardized data formats, different information systems can not be achieved sharing and interoperability. The problems above must be resolved from the perspective of formal semantics.
By researching on UMLS , Ontology and Object-oriented Database, the article puts forward a medical cases model based on Ontology. The model can describe and memorize medical information in semantic layer. At the same time, it can achieve inter-operation of information in isomerous medical cases. The following are the details:
1. Forming idea and basic structure of cases model are advanced. The model is driven by Ontology, including application layer, semantic layer, and data layer. Medical ontological dictionary and object-oriented database on data layer are base and core of this model.
2. In the formation of Medical ontological base a mixed strategy is raised, that is, medical ontological dictionary is formed by whole-ontological dictionary and part-ontological base. This dictionary has unified ontology foundation, making the inter-operation of information in isomerous medical cases possible, and increasing the search efficiency and accuracy at a certain extent.
3. Object-oriented Database in the model can express semantic information effectively. Ontology is introduced in defining Object-oriented Database to strengthen semantic expression, simplify process, and increase the store efficiency and utilization ratio at a certain extent.
4. In the research on noumena mapping, a new arithmetic about concept comparability computing is given and validated by experiment. The arithmetic can ascertain concept comparability among different noumena, establish mapping rules of different medical noumena and support the inter-operation of information in isomerous medical cases. So the study is valuable both in theory and practice.
本文通过对一体化医学语言系统、Ontology(本体论)、对象数据库等技术的研究,提出基于本体的医学案例库模型。该模型能够在语义层次上描述和存储医学信息,并能实现异构医学案例库之间的信息互操作。具体的研究内容有:
1.文中提出了案例库模型的构建思想和基本结构。该模型是由本体驱动,包括应用层、语义层和数据层三层结构,其中数据层中的医学本体库和对象数据库是整个模型的基础与核心。
2.文中在医学本体库的构建中提出了一种混合策略,即是由全局本体库(概念词典)和局部本体库共同构建医学本体库。以这种策略构建的医学本体库,具有统一的本体基础(概念词典),从而使得异构案例库之间的信息数据互操作成为可能,并在一定程度上提高了医学信息检索的有效性和准确率。
3.模型中采用的对象数据库是一种能够有效表达数据语义信息的数据库模式,通过将本体的方法引入对象数据库模型的定义过程中,以此增强数据库模型的语义表达能力,同时又简化了语义冲突的化解过程,这在一定程度上提高医学信息的存储效率和复用率。
4.文中在对本体映射的研究中,结合本文的模型特点,提出了一种概念相似度计算算法,并对算法的有效性进行了实验验证。该算法能够有效的确定异构本体之间的概念相似程度,为异构医学信息系统之间的本体映射提供了算法支持。以上的研究具有一定的理论价值和实际意义。
Currently, in the medical field, the case is extremely valuable source of knowledge, electronic medical informatics case is the realization of goals, and has been a practical application. But now the case of electronic data is in the form of text, its semantic content of computer information can not handle, and will be difficult to achieve automated knowledge acquisition. Moreover, as the electronic case is still not standardized data formats, different information systems can not be achieved sharing and interoperability. The problems above must be resolved from the perspective of formal semantics.
By researching on UMLS , Ontology and Object-oriented Database, the article puts forward a medical cases model based on Ontology. The model can describe and memorize medical information in semantic layer. At the same time, it can achieve inter-operation of information in isomerous medical cases. The following are the details:
1. Forming idea and basic structure of cases model are advanced. The model is driven by Ontology, including application layer, semantic layer, and data layer. Medical ontological dictionary and object-oriented database on data layer are base and core of this model.
2. In the formation of Medical ontological base a mixed strategy is raised, that is, medical ontological dictionary is formed by whole-ontological dictionary and part-ontological base. This dictionary has unified ontology foundation, making the inter-operation of information in isomerous medical cases possible, and increasing the search efficiency and accuracy at a certain extent.
3. Object-oriented Database in the model can express semantic information effectively. Ontology is introduced in defining Object-oriented Database to strengthen semantic expression, simplify process, and increase the store efficiency and utilization ratio at a certain extent.
4. In the research on noumena mapping, a new arithmetic about concept comparability computing is given and validated by experiment. The arithmetic can ascertain concept comparability among different noumena, establish mapping rules of different medical noumena and support the inter-operation of information in isomerous medical cases. So the study is valuable both in theory and practice.
引文
[1]王意洁.面向对象的数据库技术[M].北京:电子工业出版社,2003.
[2]黄碧云,方平.信息检索系统中情报语言的一体化[J].情报杂志,2002,21(3):49-50.
[3]贺玲勇.联机一体化词表的原理与实践(一):概念查找和语义关系显示的实现[J].现代图书情报技术,1995,(2):18-23.
[4]尹爱宁,张汝恩.建立《中医药一体化语言系统》[J].中国中药信息杂志,2003,10(3):90-91.
[5]俞宣孟.本体论研究[M].上海:上海人民出版社,1999.
[6]www.nlm.nih.gov/research/umls(OL).
[7]邓志鸿等.Ontology研究综述[J].北京大学学报(自然科学版),2002,38(5):730-738
[8]Gruber,T.Ontolingua:A translation approach to portable ontology specifi-cations[J].Knowledge Acquisition,1993,5(2):199-200.
[9]Borst W N.Construction of Engineering Ontologies for Knowledge Sharing and Reuse[J].PhD thesis,University of Twente,Enschede,1997.
[10]Studer R,Benjamins V R,Fensel D.Knowledge Engineering,Principles and Methods[J].Data and Knowledge Engineering,1998,25(122):161-197.
[11]方平.试论一体化医学语言系统(UMLS)超级叙词表的特点[J].图书情报工作,1998,(10).26-29.
[12]www.nlm.nih.gov/pubs/factsheets(OL).
[13]张爱莲一体化医学语言系统研究进展[J].医学情报工作,2005,26(2):81-84.
[14]McCray AT.An Upper Level Ontology for the Biomedical Domain (J).Comp Funct Genom,2003,4:80-8.
[15]胡德华,方平一体化医学语言系统(UMLS)及其对我国情报检索语言的启示[J].情报学报,2000,19(2):158-163.
[16]胡铁军,李丹亚,诸文雁等.统一的中国医学语言系统研究进展[J].中华医学图书馆杂志,2001,10(2):1-3.
[17]尹爱宁,张汝恩.建立《中医药一体化语言系统》(J).中国中医药信息杂志,2003,10(3):90-91.
[18]Guarino N.Semantic:Formal Ontological Distinctions for Information Organization,Extraction,and Integration.In:Pazienza M T,eds.Information Extraction:A Multidisciplinary Approach to an Emerging Information Technology,Springer Verlag,1997,139-170.
[19]李景,苏晓鹭,钱平.构建领域本体的方法[J].《计算机与农业》,2003,7:7-10.
[20]Anita Burgun,Olivier Bodenteider,Mapping the UMLS Semantic Network into General Ontologies(M).Proceedings of AMIA annual Symposium,2001:86-90.
[21]Perez A G,Benjamins V R.Overview of Knowledge Sharing and Reuse Components:Ontologies and Problem-Solving Methods[J].In:Stockholm,Benjamin's,Chandrasekaran A,eds.Proceeding of the IJCAI 99 workshop on Ontologies and Problem Solving Methods(KRR5)1999:1-15
[22]梁红.都柏林核心元数据在数字图书馆资源组织中的应用与思考[J].现代情报,2004,(2):171.
[23]韩夏,张晓林.描述医学资源的元数据方案[J].图书情报工作,2003,(12):56.
[24]US National Library of Medicine.NLM Metadata Schema(M/OL)(2004-12-08).http://www.nlm.nih.gov/tsd/cataloging/metafilenew.html.
[25]Malet G,Munoz F,Appleyard R.A model for enhancing internet medical document retrieval with "medical coremetadata"[J].J Am Med Inform Assoc,1999,6(2):163.
[26]Thirion B,Douyere M,Soualmia LF,et al.Metadata element sets in the CISMeF quality-controlled health gateway[J].Stud Health Technol Inform,2003,95:707.
[27]Yukiko Sakai.Metadata for evidence based medicine resources,Proc Inter Conf on Dublin Core and Metadata Ap2 placations 2001[C/OL].2001 NII Tokyo Japan,(2001-11-02).http://www.nii.ac.jp/dc2001/proceedings/product/paper-12.pdf.
[28]M R Genesereth,R E Fikes.Knowledge interchange format,version 3.0reference manual[R].Technical Report Logic-92-1,Computer Science Department,Stanford University,1992.
[29]Ontolingua[DB/OL].http://www.ksl.stanford.edu/software/ontolingua.
[30]CycL[DB/OL].http://www.cyc.com/tech.html.
[31]Loom[DB/OL].http://www.isi.edu/isd/LOOM/LOOM-HOME.html.
[32]Xuezhong Zhou.Ontology development for unified traditional Chinese medical language system[J].Artificial Intelligence in Medicine,2004,32:15-27.
[33]Gruber N,Welty C.A Formal Ontology of Properties.In:Dieg R,Corby O,eds.the Proceedings of the 12th International Conference on Knowledge Engineering and Knowledge Management(EKAW'2000),Springer Verlag,2000,97-112.
[34]Abraham Silberschatz,Henry F Korth,S Sudarshan.Database System Concepts[M].The McGraw-Hill Companies Inc,2006.
[35]Wache H,Vgele T,Visser U,Stuckenschmidt H,Schuster G,Neumann H,Hubner S.Ontology-Based integration of information—A survey of existing approaches.In:Stuckenschmidt H,ed.Proc.of the IJCAI 2001.New York:IEEE Press,2001.108-118.
[36]U.S.Dep.of Health and Human Services.National Institutes of Health National Library of Medicine.UMLS Knowledge Sources 8th ed,January1999.
[37]Guide to the Classification and Indexing System.Elsevier Science Publishers B.V.,1983.
[38]方平.EMTree Thesaurus的控制方式及特点探讨.医学情报作,1996,17(3):47-50.
[39]W3C,Harmelen F,Hendler J,Horrocks I,et al.OWL Web Ontology Language Reference[EB/OL].http://www.w3.org/tr/owl-ref,2004.
[40]宋炜,张铭.语义网简明教程[M].北京:高等教育出版社,2004.
[41]李毅,庞景安.基于多层次概念语义网络结构的中文医学信息语义标引体系和语义检索模型研究[J].情报学报,2003,22(4):403-401.
[42]周希瑗.白内障及治疗进展[J].中国眼科杂志,2003,12(3):40-43.
[43]张效房.白内障的治疗和手术[J].中国残疾人,2004,10(2):87-89.
[44]施玉英,寿涵荣.白内障的诊断及类型[J].中国残疾人,1999,13(3):60-64.
[45]Wouters C,Dillon T,Rahayu W,Chang E,Meersman R.A practical approach to the derivation of materialized ontology view.Web Information Systems,Idea Group Publishing,2004.191-226.
[46]Farquhar,A Fikes R,Rice J.The ontolingua server:a tool for collaborative ontology construction[J].International Journal of Human-Computer Studies,1997,46(6):707-728
[47]黄烟波等.本体映射方法研究[J].计算机工程与应用,2005,(18):27-31.
[1]毛雪岷,笪磊.语义网络技术在电子病历中的应用探讨,中国医疗器械杂志(已录用).
[2]黄碧云,方平.信息检索系统中情报语言的一体化[J].情报杂志,2002,21(3):49-50.
[3]贺玲勇.联机一体化词表的原理与实践(一):概念查找和语义关系显示的实现[J].现代图书情报技术,1995,(2):18-23.
[4]尹爱宁,张汝恩.建立《中医药一体化语言系统》[J].中国中药信息杂志,2003,10(3):90-91.
[5]俞宣孟.本体论研究[M].上海:上海人民出版社,1999.
[6]www.nlm.nih.gov/research/umls(OL).
[7]邓志鸿等.Ontology研究综述[J].北京大学学报(自然科学版),2002,38(5):730-738
[8]Gruber,T.Ontolingua:A translation approach to portable ontology specifi-cations[J].Knowledge Acquisition,1993,5(2):199-200.
[9]Borst W N.Construction of Engineering Ontologies for Knowledge Sharing and Reuse[J].PhD thesis,University of Twente,Enschede,1997.
[10]Studer R,Benjamins V R,Fensel D.Knowledge Engineering,Principles and Methods[J].Data and Knowledge Engineering,1998,25(122):161-197.
[11]方平.试论一体化医学语言系统(UMLS)超级叙词表的特点[J].图书情报工作,1998,(10).26-29.
[12]www.nlm.nih.gov/pubs/factsheets(OL).
[13]张爱莲一体化医学语言系统研究进展[J].医学情报工作,2005,26(2):81-84.
[14]McCray AT.An Upper Level Ontology for the Biomedical Domain (J).Comp Funct Genom,2003,4:80-8.
[15]胡德华,方平一体化医学语言系统(UMLS)及其对我国情报检索语言的启示[J].情报学报,2000,19(2):158-163.
[16]胡铁军,李丹亚,诸文雁等.统一的中国医学语言系统研究进展[J].中华医学图书馆杂志,2001,10(2):1-3.
[17]尹爱宁,张汝恩.建立《中医药一体化语言系统》(J).中国中医药信息杂志,2003,10(3):90-91.
[18]Guarino N.Semantic:Formal Ontological Distinctions for Information Organization,Extraction,and Integration.In:Pazienza M T,eds.Information Extraction:A Multidisciplinary Approach to an Emerging Information Technology,Springer Verlag,1997,139-170.
[19]李景,苏晓鹭,钱平.构建领域本体的方法[J].《计算机与农业》,2003,7:7-10.
[20]Anita Burgun,Olivier Bodenteider,Mapping the UMLS Semantic Network into General Ontologies(M).Proceedings of AMIA annual Symposium,2001:86-90.
[21]Perez A G,Benjamins V R.Overview of Knowledge Sharing and Reuse Components:Ontologies and Problem-Solving Methods[J].In:Stockholm,Benjamin's,Chandrasekaran A,eds.Proceeding of the IJCAI 99 workshop on Ontologies and Problem Solving Methods(KRR5)1999:1-15
[22]梁红.都柏林核心元数据在数字图书馆资源组织中的应用与思考[J].现代情报,2004,(2):171.
[23]韩夏,张晓林.描述医学资源的元数据方案[J].图书情报工作,2003,(12):56.
[24]US National Library of Medicine.NLM Metadata Schema(M/OL)(2004-12-08).http://www.nlm.nih.gov/tsd/cataloging/metafilenew.html.
[25]Malet G,Munoz F,Appleyard R.A model for enhancing internet medical document retrieval with "medical coremetadata"[J].J Am Med Inform Assoc,1999,6(2):163.
[26]Thirion B,Douyere M,Soualmia LF,et al.Metadata element sets in the CISMeF quality-controlled health gateway[J].Stud Health Technol Inform,2003,95:707.
[27]Yukiko Sakai.Metadata for evidence based medicine resources,Proc Inter Conf on Dublin Core and Metadata Ap2 placations 2001[C/OL].2001 NII Tokyo Japan,(2001-11-02).http://www.nii.ac.jp/dc2001/proceedings/product/paper-12.pdf.
[28]M R Genesereth,R E Fikes.Knowledge interchange format,version 3.0reference manual[R].Technical Report Logic-92-1,Computer Science Department,Stanford University,1992.
[29]Ontolingua[DB/OL].http://www.ksl.stanford.edu/software/ontolingua.
[30]CycL[DB/OL].http://www.cyc.com/tech.html.
[31]Loom[DB/OL].http://www.isi.edu/isd/LOOM/LOOM-HOME.html.
[32]Xuezhong Zhou.Ontology development for unified traditional Chinese medical language system[J].Artificial Intelligence in Medicine,2004,32:15-27.
[33]Gruber N,Welty C.A Formal Ontology of Properties.In:Dieg R,Corby O,eds.the Proceedings of the 12th International Conference on Knowledge Engineering and Knowledge Management(EKAW'2000),Springer Verlag,2000,97-112.
[34]Abraham Silberschatz,Henry F Korth,S Sudarshan.Database System Concepts[M].The McGraw-Hill Companies Inc,2006.
[35]Wache H,Vgele T,Visser U,Stuckenschmidt H,Schuster G,Neumann H,Hubner S.Ontology-Based integration of information—A survey of existing approaches.In:Stuckenschmidt H,ed.Proc.of the IJCAI 2001.New York:IEEE Press,2001.108-118.
[36]U.S.Dep.of Health and Human Services.National Institutes of Health National Library of Medicine.UMLS Knowledge Sources 8th ed,January1999.
[37]Guide to the Classification and Indexing System.Elsevier Science Publishers B.V.,1983.
[38]方平.EMTree Thesaurus的控制方式及特点探讨.医学情报作,1996,17(3):47-50.
[39]W3C,Harmelen F,Hendler J,Horrocks I,et al.OWL Web Ontology Language Reference[EB/OL].http://www.w3.org/tr/owl-ref,2004.
[40]宋炜,张铭.语义网简明教程[M].北京:高等教育出版社,2004.
[41]李毅,庞景安.基于多层次概念语义网络结构的中文医学信息语义标引体系和语义检索模型研究[J].情报学报,2003,22(4):403-401.
[42]周希瑗.白内障及治疗进展[J].中国眼科杂志,2003,12(3):40-43.
[43]张效房.白内障的治疗和手术[J].中国残疾人,2004,10(2):87-89.
[44]施玉英,寿涵荣.白内障的诊断及类型[J].中国残疾人,1999,13(3):60-64.
[45]Wouters C,Dillon T,Rahayu W,Chang E,Meersman R.A practical approach to the derivation of materialized ontology view.Web Information Systems,Idea Group Publishing,2004.191-226.
[46]Farquhar,A Fikes R,Rice J.The ontolingua server:a tool for collaborative ontology construction[J].International Journal of Human-Computer Studies,1997,46(6):707-728
[47]黄烟波等.本体映射方法研究[J].计算机工程与应用,2005,(18):27-31.
[1]毛雪岷,笪磊.语义网络技术在电子病历中的应用探讨,中国医疗器械杂志(已录用).