Evaluation of the relevance of adverse drug reaction based on ERNIE-DPCNN

doi:10.19803/j.1672-8629.20230632

Abstract

Abstract: Objective To establish a model for evaluation of ADR correlations in order to make the related evaluation more efficient and objective. Methods A total of 7 301 pieces of annotated data on adverse reaction reports obtained from literature and Internet sources were used for knowledge extraction to construct a knowledge graph about adverse drug reactions before a knowledge-driven automatic evaluation model of ERNIE-DPCNN relevance was established. Results The precision, recall and F1 value of the knowledge graph combined with the ERNIE-DPCNN model in the test set reached 82.18%, 81.40% and 81.21%, respectively, which yielded higher values than other models. Conclusion The method based on knowledge graphs combined with the ERNIE-DPCNN model can effectively improve the efficiency and accuracy of correlation evaluation of adverse drug reactions and reduce errors that arise from subjective evaluation, which is of referential value for automated evaluation based on artificial intelligence.

Key words: adverse drug reaction (ADR), ERNIE-DPCNN model, knowledge graph, correlations of evaluation, natural language processing, deep learning, artificial intelligence

CLC Number:

R954
R994.11

JIA Jinsheng, LIU Hongliang, WANG Qing, HOU Yongfang, LI Xinling. Evaluation of the relevance of adverse drug reaction based on ERNIE-DPCNN[J]. Chinese Journal of Pharmacovigilance, 2024, 21(2): 163-166.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.zgywjj.com/EN/10.19803/j.1672-8629.20230632

https://www.zgywjj.com/EN/Y2024/V21/I2/163

References

[1] CHEN SQ, ZHENG R, LI YP, et al.Causality assessment of adverse drug reactions and its guiding significance for post-evaluation of chinese patent medicine[J]. World Science and Technology/Modernization of Traditional Chinese Medicine and Materia Medica(世界科学技术中医药现代化), 2018, 20(10): 1729-1733.
[2] LI B, GAO R, LI R, et al.Causal determination of the adverse events and adverse drug reactions in drug clinical trials[J]. Chinese Journal of New Drugs(中国新药杂志), 2014, 23(12): 1465-1470.
[3] HUANG Q, WEN ZH.An initiative to establish coordinated and consistent causality assessment criteria for adverse drug reaction in clinical trials[J]. Chinese Journal of New Drugs(中国新药杂志), 2021, 30(12): 1132-1136.
[4] JI S, PAN S, CAMBRIA E, et al.A survey on knowledge graphs: representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(2): 494-514.
[5] SINGHAL A. Introducing the knowledge graph: things, not strings [EB/OL].(2012-05-16)[2023-10-01]. https://goo-gleblog.blogspot.com/2012/05/introduc-ing-knowledge-graph-things-not.html.
[6] FAN YY, LI ZM.Research and application progress of chinese medical knowledge graph[J]. Journal of Frontiers of Computer Science and Technology(计算机科学与探索), 2022, 1(10): 2219-2233.
[7] DONG WB, SUN SL, YIN MZ.Research and development of medical knowledge graph reasoning[J]. Journal of Frontiers of Computer Science and Technology(计算机科学与探索), 2022, 16(6): 1193-1213.
[8] PENG QQ, WANG D.Medical text classification model based on deep learning[J]. Electronic Design Engineering(电子设计工程), 2023, 31(5): 51-54,60.
[9] XU L, LI DW, ZHANG HQ, et al.Medical text classification based on neural network[J]. Computer Engineering & Science(计算机工程与科学), 2023, 45(6): 1116-1122.
[10] ZHANG JX, ZHANG XS, WU CX, et al.Survey of knowledge graph construction techniques[J]. Computer Engineering(计算机工程), 2022, 48(3): 23-37.
[11] XU AY, HU KF, YANG TAO.Construction of knowledge map of TCM diagnosis and treatment of lung cancer based on neo4j[J]. Modernization of Traditional Chinese Medicine and Materia Medica-World Science and Technology(世界科学技术中医药现代化), 2023, 25(4): 1456-1461.
[12] XU ST, SUN M.Construction and application of knowledge graph in chinese electronic medical records based on name entity recognition and neo4j[J]. Journal of Medical Informatics(医学信息学杂志), 2022, 43(12): 50-56.
[13] JOHNSON R, ZHANG T.Deep pyramid convolutional neural networks for text categorization[C]. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017: 562-570.
[14] HU Y.Doctor-patient dialogue text classification based on ERNIE-CNN model[J]. Information & Computer(信息与电脑理论版), 2022, 34(11): 43-45.
[15] CHANG JH, WU YZ.Chinese medical text classification based on ERNIE-BiGRU model[J]. Computer Knowledge and Technology(电脑知识与技术), 2022, 18(1): 101-104.