Drug Risk Knowledge Discovery for Western Medicines Based on Knowledge Graph Link Prediction

Authors

• Jianxiang WEI, (1) School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210003; (2) Library, Nanjing University of Posts and Telecommunications, Nanjing 210023
• MA Hengyuan MA, School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210003
• Yuehong SUN, School of Mathematical Sciences, Nanjing Normal University, Nanjing 210023
• Wenwen DU, School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210003
• Letian HU, School of Management, Nanjing University of Posts and Telecommunications, Nanjing 210003

Keywords

knowledge graph; link prediction; knowledge reasoning; risk prediction; pharmacovigilance

Abstract

[Purpose/significance] The risk information contained in drug instructions is usually incomplete, and some new adverse reactions can only be discovered in actual clinical use. This paper proposes an information organization and knowledge discovery method for pharmacovigilance, in order to timely and accurately identify missing risk knowledge in drug instructions. [Method/process] Drug instructions of 8 152 Western medicines are collected as the research data; On the basis of ontology construction, data annotation, and model training, the UIE model is used to jointly extract entity and relationship triplets from the research data; A new knowledge graph link prediction method CompGCN-RotatE, is proposed, and performance comparison experiments are conducted with classical RotatE on multiple datasets; Empirical research is conducted by using the proposed method. [Result/conclusion] Compared to the classical Rotate method, research results show that our method has significant improvements in the three indicators, MRR, Hits@3 and Hits@10, and achieve performance of 58.7%, 65.6% and 80.5% respectively on the research data. The method proposed can effectively discover drug risk knowledge that is not mentioned in drug instructions but is actually monitored, providing new ideas for pharmacovigilance in China.

First Page

45

Last Page

56

Submission Date

February 2025

Revision Date

March 2025

Acceptance Date

June 2025

Publication Date

January 2026

Digital Object Identifier (DOI)

ꎺ 10.19809/j.cnki.kjqbyj.2026.01.005

Recommended Citation

WEI, Jianxiang; MA, MA Hengyuan; SUN, Yuehong; DU, Wenwen; and HU, Letian (2026) "Drug Risk Knowledge Discovery for Western Medicines Based on Knowledge Graph Link Prediction," Journal of Scientific Information Research: Vol. 8: Iss. 1, Article 5.
DOI: ꎺ 10.19809/j.cnki.kjqbyj.2026.01.005
Available at: https://eng.kjqbyj.com/journal/vol8/iss1/5

Reference

[1] EDWARDS I R，ARONSON J K.Adverse drug reactions：Definitions，diagnosis，and management[J].The Lancet，2000，356（9237）：1255-1259.
[2] BÉGAUD B.Methodological approaches in pharmacoepidemiology：Application to spontaneous reporting[M].Amsterdam：Elsevier Science Publishers B.V，1993.
[3] WHO.Collaborating Centre for International Drug Monitoring.Dictionary of pharmaceutical medicine[M].Springer Vienna，2009.
[4] 国家药品不良反应监测中心.国家药品不良反应监测年度报告（2022年）[EB/OL].（2023-03-24）[2024-01-01].https：//www.cdr-adr.org.cn/drug_1/aqjs_1/drug_aqjs_sjbg/202303/t20230324_50019.html.
[5] 苏新宁.传统知识组织方法的智能力[J].科技情报研究，2024，6（1）：1-9.
[6] ROUTRAY R，TETARENKO N，ABU-ASSAL C，et al.Application of Augmented Intelligence for Pharmacovigilance Case Seriousness Determination[J].Drug Safety，2020，43（1）：57-66.
[7] 王涛，郑明节，刘红亮，等.人工智能在美国药物警戒中的应用现状及启示[J].中国药物警戒，2023，20（10）：1129-1133.
[8] BALL R，DAL PAN G.“Artificial Intelligence”for pharmacovigilance：ready for prime time?[J].Drug safety，2022，45（5）：429-438.
[9] MORO A，INVERNIZZI N.The thalidomide tragedy：the struggle for victims' rights and improved pharmaceutical regulation[J].Hist Cienc Saude Manguinhos，2017，24（3）：603-622.
[10] SHANKAR P R.The Importance of Pharmacovigilance[J].Journal of Clinical & Diagnostic Research，2008（6）：1246-1247.
[11] BOUSQUET C，HENEGAR C，LOUET A L，et al.Implementation of automated signal generation in pharmacovigilance using a knowledge-based approach[J].International Journal of Medical Informatics，2005，74（7-8）：563-571.
[12] HÄRMARK L，GROOTHEEST A C.Pharmacovigilance：methods，recent developments and future perspectives[J].European Journal of Clinical Pharmacology，2008，64（8）：743-752.
[13] MONTASTRUC J L，SOMMET A，BAGHERI H，et al.Benefits and strengths of the disproportionality analysis for identification of adverse drug reactions in a pharmacovigilance database[J].British Journal of Clinical Pharmacology，2011，72（6）：905-908.
[14] 杨羽，王胜锋，詹思延.社交媒体数据在药品上市后安全性监测的应用[J].北京大学学报（医学版），2021，53（3）：623-627.
[15] LARDON J，BELLET F，ABOUKHAMIS R，et al.Evaluating twitter as a complementary data source for pharmacovigilance[J].Expert Opinion on Drug Safety，2018，17（8）：763-774.
[16] LEAMAN R，WOJTULEWICZ L，SULLIVAN R，et al.Towards internet-age pharmacovigilance：extracting adverse drug reactions from user posts to health-related social networks[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics，Uppsala Sweden：2010：117-125.
[17] WHITE R W，TATONETTI N P，SHAH N H，et al.Web-scale pharmacovigilance：listening to signals from the crowd[J].Journal of the American Medical Informatics Association，2013，20（3）：404-408.
[18] ROCHE V，ROBERT J P，SALAM H.A holistic AI-based approach for pharmacovigilance optimization from patients behavior on social media[J].Artificial Intelligence in Medicine，2023，144：102638.
[19] SALATHE M.Digital pharmacovigilance and disease surveillance：combining traditional and big-data systems for better public health[J].Journal of Infectious Diseases，2016，214（Suppl 4）：S399-S403.
[20] 王广平，胡骏，丁静.药物警戒制度的信息机制分析[J].中国医药导刊，2020，22（10）：709-713.
[21] JIA K.Machine learning on mining potential adverse drug reactions for pharmacovigilance[C]//Proceedings of the 4ths International Conference on Data Science and Information Technology，Shanghai：2021，295-298.
[22] MARINKA Z，MONICA A，JURE L.Modeling polypharmacy side effects with graph convolutional networks[J].Bioinformatics，2018，34（13）：i457-i466.
[23] BANG S，JHEE J H，SHIN H.Polypharmacy side-effect prediction with enhanced interpretability based on graph feature attention network[J].Bioinformatics，2021，37（18）：2955-2962.
[24] NYAMABO A K，YU H，SHI J Y.SSI-DDI：substructure-substructure interactions for drug-drug interaction prediction[J].Briefings in Bioinformatics，2021，22（6）：bbab133（1-10）.
[25] MOHAMED S K，NOUNU A，NOVÁCEK V.Biological applications of knowledge graph embedding models[J].Briefings in Bioinformatics，2021，22（2）：1679-1693.
[26] EL-ALLALY ED，SARROUTI M，EN-NAHNAHI N，et al.DeepCADRME：A deep neural model for complex adverse drug reaction mentions extraction-ScienceDirect[J].Pattern Recognition Letters，2021，143：27-35.
[27] 杨乐乐，龙海，姚克宇，等.基于本体推理和语义网检索的中西药相互作用知识发现研究[J].中华中医药学刊，2024，42（9）：13-17.
[28] 洪怡敏，张晗，白智瑛.面向重大慢性疾病健康管理的知识图谱构建及应用[J].情报理论与实践，2024，47（8）：180-189，210.
[29] 陈明，刘蓉，熊回香.基于医疗知识图谱的智能问答系统研究[J].情报科学，2023，41（12）：118-126.
[30] 王成文，熊励.基于知识图谱的突发公共卫生事件辅助诊疗研究[J].情报科学，2023，41（4）：164-174.
[31] 熊励，王成文，王锟.基于事件本体的疫情知识库构建策略[J].图书情报工作，2021，65（14）：138-148.
[32] WEI Z P，SU J L，WANG Y，et al.A novel cascade binary tagging framework for relational triple extraction[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Online：2020：1476-1488.
[33] ZHENG H Y，WEN R，CHEN X，et al.PRGC：Potential relation and global correspondence based joint relational triple extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.Bangkok：2021，6225-6235.
[34] LU Y J，LIU Q，DAI D，et al.Unified structure generation for universal information extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.Dublin：2022，5755-5772.
[35] SHANG C，TANG Y，HUANG J，et al.End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion[C]//Proceedings of the 33th AAAI Conference on Artificial Intelligence.Honolulu：2019，3060-3067.
[36] VASHISHTH S，SANYAL S，NITIN V，et al.Composition-based Multi-Relational Graph Convolutional Networks[C]//Proceedings of the 8th International Conference on Learning Representations.Suzhou：2020，1-16.
[37] SUN Z Q，DENG Z H，NIE J Y，et al.RotatE：knowledge graph embedding by relational rotation in complex space[C]//Proceedings of the 7th International Conference on Learning Representations.New Orleans：2019，1-18.
[38] TOUTANOVA K，CHEN D.Observed versus latent features for knowledge base and text inference[C]//Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality.2015，57-66.
[39] NICKEL M，TRESP V，KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//Proceedings of the 28th International Conference on Machine Learning.Bellevue：2011，3104482-3104584.
[40] Dettmers T，Minervini P，Stenetorp P，et al.Convolutional 2D Knowledge Graph Embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence，New Orleans：2018：1811-1818.