传统的知识建模方法在医学场景下面临着知识复杂性高、难以通过传统三元组的方式精确表达等问题,需要研究新的本体对医学知识进行建模。该文提出一种应用于高血压领域的三层超关系知识图谱模型(Triple-view Hypertension Hyper-relational Knowledge Graph,THH-KG),该方法基于超关系知识图谱模型搭建计算层、概念层、实例层三层图谱架构,实现多元的医学逻辑规则、概念知识和实例知识的联合表达。此外,该文还提出了在普通图数据库中超关系知识图谱的通用存储方法,且基于该方法设计了高血压知识图谱推理解释引擎(Hypertension Knowledge Graph Reasoning Engine,HKG-RE),实现了基于医学规则的用药推荐辅助决策应用。上述方法在对108位真实高血压患者的用药推荐实验中正确率达到了97.2%。
Abstract
Traditional knowledge modeling methods have been always being plagued by the high complexity of hypertension knowledge, failing in accurate knowledge representation by the triples. In this paper, we propose a Triple-view Hypertension Hyper-relational Knowledge Graph (THH-KG). It builds a three-layer graph architecture containing calculation layer, concept layer and instance layer, based on which the joint expression of multiple medical logic rules, conceptual knowledge and patient knowledge are realized. Additionally, we propose a general storage method of hyper-relational knowledge graph in common graph database, on which a Hypertension Knowledge Graph Reasoning Engine (HKG-RE) is also established. Results in medication decision experiment witness 97.2% positive rate out of 108 patients with hypertension.
关键词
多元关系 /
超关系知识图谱 /
高血压 /
用药推荐
{{custom_keyword}} /
Key words
multi-relation /
hyper-relational knowledge graph /
hypertension /
medical recommendation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] PAULHEIM H. Knowledge graph refinement: A survey of approaches and evaluationmethods[J]. Semantic Web, 2017, 8(3): 489-508.
[2] 中国高血压防治指南修订委员会,高血压联盟(中国),中华医学会心血管病学分会,等.中国高血压防治指南(2018年修订版)[J]. 中国心血管杂志, 2019, 24(01): 24-56.
[3] ROSSO P, YANG D, CUDR-MAUROUX P. Beyond triplets: Hyper-relational knowledge graph embedding for link prediction[C]//Proceedings of the Web Conference. New York: ACM, 2020: 1885-1896.
[4] WEN J F, LI J X, MAO YY, et al. On the representation and embedding of knowledge bases beyond binary relations[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2016:1300-1307.
[5] FATEMI B, TASLAKIAN P, VAZQUEZ D, et al. Knowledge hypergraphs: prediction beyond binary relations[C]//Proceedings of the 29th International Joint Conferences on Artificial Intelligence. Palo Alto, CA: AAAI Press, 2021: 2191-2197.
[6] VERE J, GIBSON B. Evidence-based medicine as science.[J]. Journal of Evaluation in Clinical Practice, 2019, 25(6) : 997-1002.
[7] 胡志磊,靳小龙,陈剑赟,等.事件图谱的构建、推理与应用[J].大数据,2021,7(03):80-96.
[8] JIANG H,BAO Q, CHENG Q, et al. Complex relation extraction: Challenges and opportunities[J]. arXiv preprint arXiv:2012.04821, 2020.
[9] BODENREIDER O. The unified medical language system: Integrating biomedical terminology[J]. Nucleic Acids Research, 2004, 32(suppl_1): D267-D270.
[10] LEE D, CORNET R, LAU F, et al. A survey of SNOMED CT implementations[J]. Journal of Biomedical Informatics, 2013, 46(1): 87-96.
[11] GENE Ontology Consortium. The gene ontology resource: 20 years and still going strong[J]. Nucleic Acids Research, 2019, 47(D1): D330-D338.
[12] 李丹亚,胡铁军,李军莲,等.中文一体化医学语言系统的构建与应用[J].情报杂志,2011,30(02):147-151.
[13] 于彤,崔蒙,李海燕,等.中医药学语言系统的语义网络框架:一个面向中医药领域的规范化顶层本体[J].中国数字医学,2014,9(01):44-47.
[14] 奥德玛,杨云飞,穗志方,等.中文医学知识图谱CMeKG构建初探[J].中文信息学报,2019,33(10):1-9.
[15] ROSPOCHER M, VAN ERP M, VOSSEN P, et al. Building event-centric knowledge graphs from news[J]. Journal of Web Semantics, 2016, 37-38: 132-151.
[16] WEN J, LI J, MAO Y, et al. On the representation and embedding of knowledge bases beyond binary relations[C]//Proceedings of the 25th International Joint Conference on Artificial Intelligence. San Francisco, CA: Margan Kaufmann, 2016: 1300-1307.
[17] ZHANG R, LI J, MEI J, et al. Scalable instance reconstruction in knowledge bases via relatedness affiliated embedding[C]//Proceedings of the World Wide Web Conference. New York: ACM, 2018: 1185-1194.
[18] BRETTO A.Applications of Hypergraph theory: A Brief Overview[M]. Hgpergraph Theary: Heidelberg, Springer,2013:111-116.
[19] GUAN S, JIN X,GUO J, et al. Neuinfer: Knowledge inference on n-ary facts[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, PA: ACL, 2020: 6141-6151.
[20] GALKIN M, TRIVEDI P, MAHESHWARI G, et al. Message passing for hyper-relational knowledge graphs[J]. arXiv preprint arXiv:2009.10847, 2020.
[21] YAN S, ZHANG Z, SUN X, et al. HYPER2: Hyperbolic embedding for hyper-relational link prediction[J]. Neurocomputing, 2022, 492: 440-451.
[22] ZHOU J, HU S,LV X, et al. KACC: A multi-task benchmark for knowledge abstraction, concretization and completion[J]. arXiv preprint arXiv:2004.13631, 2020.
[23] 田玲,张谨川,张晋豪,等.知识图谱综述: 表示、构建、推理与知识超图理论[J].计算机应用, 2021, 41(08): 2161-2186.
[24] 鄂海红,张文静,肖思琪,等.深度学习实体关系抽取研究综述[J].软件学报,2019,30(06):1793-1818.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
信息网络教育部工程研究中心项目;国家自然科学基金(61902034,62176026);北京市自然科学基金(M22009)
{{custom_fund}}
PDF(4821 KB)
