优先出版 袁凯琦,等:医学知识图谱构建技术与研究进展 第35卷第7期 百科中的药物信息由医学研究者共同编辑完成。而另一方面,0 Stevens r, Baker p, Bechhofer s,eta. TAMBIS: Transparent Access 如何评估和保障提交结果的质量,也开始受到国内外学者的关 Multiple Bioinformatics Information Sources [J). Bioinformatics200016 注 4)可视化 1]刘知远,孙茂松,林衍凯,等,知识表示学习研究进展凹计算机研 知识图谱可视化的真正意义在于让人直观地了解推理的过 究与发展,2016,53(2):247-261 程与结果。而医学知识图谱可视化站在医生或病人的立场,寻[12] Turian j, Ratinov L, Bengio y. Word representations: a simple and general 求最佳的知识展示方案:病人能够理解诊断结果,医生能够利 method for semi-supervised learning ICy/ Proc of the 48th Annual Meeting 用知识图谱的动态推理过程作出合理诊断 of the Association For Computational Linguistics. Association for Computational Linguistics, 2010: 384-394. 4结束语 [13] Bordes A, Weston J, Collobert R, et al. Learning structured embeddings of 随着医疗信息化的发展,医学电子数据有了一定的积累。 knowledge bases IC]/ Proc of Conference on Artificial Intelligence. 2011 构建医疗领域的知识图谱,可以从海量数据中提炼出医疗知识,[4] Socher r, Chen d, Manning C d,etal. Reasoning with neural tensor 并合理高效地对其进行管理、共享及应用,对当今的医疗行业 networks for knowledge base completion IC) Advances in Neural 有着重要意义,也是很多企业和研究机构的研究热点。本文从 Information Processing Systems. 2013: 926-934 医疗知识图谱的构建与应用角度,综述了医疗知识图谱的相关15] Jenatton r, ROUx NL, bordes a,etal. A latent factor model for highly 背景、现有技术和应用,总结了目前医疗知识图谱面临的主要 multi-relational data [CH/ Advances in Neural Information Processing 挑战,并对其未来的研究方向进行了展望。 Systems.2012:3167-3175 医学知识图谱将知识图谱与医学知识进行结合,定会推进16] bordes a, Usunier N, Garcia-Duran a,eta. Translating embeddings for 医学数据的自动化与智能化处理,为医疗行业带来新的发展契 modeling multi-relational data [CI Advances in information 机。虽然目前对于医疗知识图谱的研究工作有了很多很有意义 rocessing systems. 2013: 2787-2795 的尝试,但总的来说还不够完善和深入,需要更进一步的研究。[17] Kleyko D. Khan s, Osipov E,etal. Modality classification of medical 希望本文能够为医疗知识图谱在国内的研究提供一些帮助与启 images with distributed representations based on cellular automata eservoir computing ICy Proc of IEEE International Symposium on Biomedical Imaging 2017. 18 Henriksson A, Zhao J, Dalianis H, et al. Ensembles of randomized trees 参考文献 [1] Singhal A. Introducing the knowledge graph: things, not strings [EB/OLI Medical Informatics and Decision Making, 2016, 16(2): 69. Officialgoogleblog,2012.https://googleblog.blogspot..co.[19侯丽,钱庆,黄利辉,等,基于本体的临床医学知识库系统构建探讨 za/2012/05/introducing- knowledge-graph-things-not html 医乎信息学杂志,2011,32(4):42-47 [2] Amarilli A, Galarraga L, Preda N, et al. Recent Topics of Research around [20]Nadkarni P, Chen R, Brandt C. UMLS concept indexing for production the YAGO Knowledge Base [M/ Web Technologies and Applications. databases UJ]. Journal of the American Medical Informatics Association, Springer International Publishing, 2014: 1-12 2001,8(1):80-91 [3] Auer S, Bizer C, Kobilarov Gi et al. DBpedia: A Nucleus for a Web of [21]Friedman C, Alderson PO, Austin J M, et al. A general natural-language Open Data [My/ The Semantic Web. Springer Berlin Heidelberg, 2007 text processor for clinical radiology [J] Journal of the American Medical 4]中医药知识图谱构建与应用团医学信息学杂志,2016,37(4):8-13 formatics Association, 1994, 1(2): 161-174 S]顾琳,基于领域本体的亚健康中医辅助诊断系统的研究及应用[D]-口22 I Wu S T, LIu h. li d.eta. FOCUS on clinical research informatics 昆明:云南师范大学,2008 Unified Medical Language System term occurrences in clinical notes:a 16] Computer-based medical consultations: MYCIN (M). Elsevier, 2012. large-scale corpus analysis J]. Journal of the American Medical [7] Redei G P. Encyclopedia of Genetics, Genomics, Proteomics and Informatics Association Jamia, 2012, 19(e1): 149-56. Informatics [M]. Springer Netherlands, 2008 23]Smith C A, Stavri P Z. Consumer Health Vocabulary [MJ/ Consumer [8] Singhal A wledge graph: things, not strings [ EB/OL Health Informatics. 2005: 122-128 [24] Uzuner O, South B R, Shen S, et al. 2010 i2b2//VA challenge on concepts, za/2012/05/introducing-knowledge-graph-things-not. htmL. ssertions, and relations in clinical text. UJ. Jourmal of the American 19] Ceusters W, Martens P, Dhaen C, et al. Link Factory: an advanced formal Medical Informatics Association, 2011, 18(5): 552-6 ontology management System IC] Proc of Interactive Tools for [25] Dogan RI, Leaman R, Lu Z NCBI disease corpus: a resource for disease Knowledge Capture Workshop. 2001: 175-204 name recognition and concept normalization. J]. Joumal of Biomedical优先出版 袁凯琦，等：医学知识图谱构建技术与研究进展 第 35 卷第 7 期 百科中的药物信息由医学研究者共同编辑完成。而另一方面， 如何评估和保障提交结果的质量，也开始受到国内外学者的关 注。 4）可视化 知识图谱可视化的真正意义在于让人直观地了解推理的过 程与结果。而医学知识图谱可视化站在医生或病人的立场，寻 求最佳的知识展示方案：病人能够理解诊断结果，医生能够利 用知识图谱的动态推理过程作出合理诊断。 4 结束语 随着医疗信息化的发展，医学电子数据有了一定的积累。 构建医疗领域的知识图谱，可以从海量数据中提炼出医疗知识， 并合理高效地对其进行管理、共享及应用，对当今的医疗行业 有着重要意义，也是很多企业和研究机构的研究热点。本文从 医疗知识图谱的构建与应用角度，综述了医疗知识图谱的相关 背景、现有技术和应用，总结了目前医疗知识图谱面临的主要 挑战，并对其未来的研究方向进行了展望。 医学知识图谱将知识图谱与医学知识进行结合，定会推进 医学数据的自动化与智能化处理，为医疗行业带来新的发展契 机。虽然目前对于医疗知识图谱的研究工作有了很多很有意义 的尝试，但总的来说还不够完善和深入，需要更进一步的研究。 希望本文能够为医疗知识图谱在国内的研究提供一些帮助与启 发。 参考文献： [1] Singhal A. Introducing the knowledge graph: things, not strings [EB/OL]. Official google blog, 2012. https://googleblog. blogspot. co. za/2012/05/introducing-knowledge-graph-things-not. html. [2] Amarilli A, Galárraga L, Preda N, et al. Recent Topics of Research around the YAGO Knowledge Base [M]// Web Technologies and Applications. Springer International Publishing, 2014: 1-12. [3] Auer S, Bizer C, Kobilarov G, et al. DBpedia: A Nucleus for a Web of Open Data [M]// The Semantic Web. Springer Berlin Heidelberg, 2007. [4] 中医药知识图谱构建与应用 [J]. 医学信息学杂志, 2016, 37 (4): 8-13. [5] 顾琳. 基于领域本体的亚健康中医辅助诊断系统的研究及应用 [D]. 昆明: 云南师范大学, 2008. [6] Computer-based medical consultations: MYCIN [M]. Elsevier, 2012. [7] Rédei G P. Encyclopedia of Genetics, Genomics, Proteomics and Informatics [M]. Springer Netherlands, 2008. [8] Singhal A. Introducing the knowledge graph: things, not strings [EB/OL]. Official google blog, 2012. https://googleblog. blogspot. co. za/2012/05/introducing-knowledge-graph-things-not. html. [9] Ceusters W, Martens P, Dhaen C, et al. LinkFactory: an advanced formal ontology management System [C]// Proc of Interactive Tools for Knowledge Capture Workshop. 2001: 175-204. [10] Stevens R, Baker P, Bechhofer S, et al. TAMBIS: Transparent Access to Multiple Bioinformatics Information Sources [J]. Bioinformatics, 2000, 16 (2): 184. [11] 刘知远, 孙茂松, 林衍凯, 等. 知识表示学习研究进展 [J]. 计算机研 究与发展, 2016, 53 (2): 247-261. [12] Turian J, Ratinov L, Bengio Y. Word representations: a simple and general method for semi-supervised learning [C]// Proc of the 48th Annual Meeting of the Association For Computational Linguistics. Association for Computational Linguistics, 2010: 384-394. [13] Bordes A, Weston J, Collobert R, et al. Learning structured embeddings of knowledge bases [C]// Proc of Conference on Artificial Intelligence. 2011. [14] Socher R, Chen D, Manning C D, et al. Reasoning with neural tensor networks for knowledge base completion [C]// Advances in Neural Information Processing Systems. 2013: 926-934. [15] Jenatton R, Roux N L, Bordes A, et al. A latent factor model for highly multi-relational data [C]// Advances in Neural Information Processing Systems. 2012: 3167-3175. [16] Bordes A, Usunier N, Garcia-Duran A, et al. Translating embeddings for modeling multi-relational data [C]// Advances in neural information processing systems. 2013: 2787-2795. [17] Kleyko D, Khan S, Osipov E, et al. Modality classification of medical images with distributed representations based on cellular automata reservoir computing [C]// Proc of IEEE International Symposium on Biomedical Imaging. 2017. [18] Henriksson A, Zhao J, Dalianis H, et al. Ensembles of randomized trees using diverse distributed representations of clinical events [J]. BMC Medical Informatics and Decision Making, 2016, 16 (2): 69. [19] 侯丽, 钱庆, 黄利辉, 等. 基于本体的临床医学知识库系统构建探讨 [J]. 医学信息学杂志, 2011, 32 (4): 42-47. [20] Nadkarni P, Chen R, Brandt C. UMLS concept indexing for production databases [J]. Journal of the American Medical Informatics Association, 2001, 8 (1): 80-91. [21] Friedman C, Alderson P O, Austin J H M, et al. A general natural-language text processor for clinical radiology [J]. Journal of the American Medical Informatics Association, 1994, 1 (2): 161-174. [22] Wu S T, Liu H, Li D, et al. FOCUS on clinical research informatics: Unified Medical Language System term occurrences in clinical notes: a large-scale corpus analysis [J]. Journal of the American Medical Informatics Association Jamia, 2012, 19 (e1): 149-56. [23] Smith C A, Stavri P Z. Consumer Health Vocabulary [M]// Consumer Health Informatics. 2005: 122-128. [24] Uzuner Ö, South B R, Shen S, et al. 2010 i2b2//VA challenge on concepts, assertions, and relations in clinical text. [J]. Journal of the American Medical Informatics Association, 2011, 18 (5): 552-6. [25] Doğan RI, Leaman R, Lu Z. NCBI disease corpus: a resource for disease name recognition and concept normalization. [J]. Journal of Biomedical