基于BERT和CNN的药物不良反应个例报道文献分类方法

doi:10.11896/jsjkx.230400049

计算机科学 ›› 2024, Vol. 51 ›› Issue (6A): 230400049-6.doi: 10.11896/jsjkx.230400049

基于BERT和CNN的药物不良反应个例报道文献分类方法

孟祥福¹, 任全莹¹, 杨东燊¹, 李可千², 姚克宇³, 朱彦³

1 辽宁工程技术大学电子与信息工程学院辽宁葫芦岛 125105
2 长春中医药大学医药信息学院长春 130117
3 中国中医科学院中医药信息研究所北京 100700

发布日期:2024-06-06
通讯作者: 朱彦(zhuyan166@126.com)
作者简介:(marxi@126.com)
基金资助:
国家自然科学基金(82174534);中央级公益性科研院所基本科研业务费专项资金(ZZ13-YQ-126,ZZ150314)

Literature Classification of Individual Reports of Adverse Drug Reactions Based on BERT and CNN

MENG Xiangfu¹, REN Quanying¹, YANG Dongshen¹, LI Keqian², YAO Keyu³, ZHU Yan³

1 College of Electronic and Information Engineering,Liaoning Technical University,Huludao,Liaoning 125105,China
2 School of Medical Information,Changchun University of Chinese Medicine,Changchun 130117,China
3 Information Institute of Traditional Chinese Medicine,Chinese Academy of Traditional Chinese Medicine,Beijing 100700,China

Published:2024-06-06
About author:MENG Xiangfu,born in 1981,Ph.D,professor,Ph.D supervisor,is a senior member of CCF(No.26143S).His main research interests include spatial big data query and analysis,artificial intelligence.
ZHU Yan,born in 1983,Ph.D,associate professor,postgraduate supervisor.His main research interests include data mining and knowledge organization of traditional Chinese medicine.
Supported by:
National Natural Science Foundation of China(82174534) and Fundamental Research Funds for the Central Public Welfare Research Institutes(ZZ13-YQ-126,ZZ150314).

摘要/Abstract

摘要： 在临床上,药物不良反应导致的死亡和用药不当造成的住院及门诊费急剧升高,成为临床安全合理用药面临的主要问题之一。目前对药物不良反应的回顾性分析和文献分析多以公开发表的文献资料为依据。学术文献作为重要的数据来源之一,如何自动批量地对其进行数据处理尤为重要。针对医药文本独特的表述方式,基于BERT及其组合模型进行文本分类技术比对实验,建立对药物不良反应个例报道文献数据进行高效快速分类的方法,进而分辨出药物不良反应的类型,有效预警药害事件。实验结果表明,使用BERT模型的分类准确率达到99.75%,其可以准确高效地对药物不良反应个例报道文献进行分类,在辅助医疗、构建医学文本结构化数据等方面均具有重要的价值和意义,进而能够更好地维护公众健康。

关键词: 药物不良反应, 个例文献报道, 医学文本分类, 深度学习, BERT

Abstract: Clinically,the death caused by adverse drug reactions and the sharp increase in hospitalization and outpatient expenses caused by improper drug use have become one of the main problems faced by clinical safe and rational drug use.At present,the research of adverse drug reactions retrospective analysis and literature analysis is mostly based on published literature information.Academic literature is one of the important sources of data,and how to automatically process data in batches is particularly important.According to the unique expression of traditional Chinese medicine text,based on BERT and its combination algorithm,through the comparison experiment of text classification technology,an efficient and fast classification method for the literature data of adverse drug reactions case reports is established,and then the types of adverse drug reactions are distinguished.Experimental results show that the classification accuracy of BERT algorithm reaches 99.75%,which can accurately and efficiently classify the reported literature of adverse drug reactions,and has important value and significance for auxiliary medical treatment and constructing structured data of medical texts.

Key words: Adverse drug reactions, Individual case literature report, Medical text classification, Deep learning, BERT

中图分类号:

TP391.1

孟祥福, 任全莹, 杨东燊, 李可千, 姚克宇, 朱彦. 基于BERT和CNN的药物不良反应个例报道文献分类方法[J]. 计算机科学, 2024, 51(6A): 230400049-6. https://doi.org/10.11896/jsjkx.230400049

MENG Xiangfu, REN Quanying, YANG Dongshen, LI Keqian, YAO Keyu, ZHU Yan. Literature Classification of Individual Reports of Adverse Drug Reactions Based on BERT and CNN[J]. Computer Science, 2024, 51(6A): 230400049-6. https://doi.org/10.11896/jsjkx.230400049

参考文献

[1]WU M Z.Extraction and Analysis of Relationships betweenDrugs and Diseases from Medical Literature[D].Shenyang:China Medical University,2010.
[2]YANG Y,BAI Y N,ZHANG Y Y,et al.Bibliometric research on 323 cases of drug fever induced by antimicrobial[J].Practical Pharmacy and Clinical Remedies,2021,24(8):722-726.
[3]LI Y L,LV M,ZHANG M.Analysis of 11 cases of levothyroxine sodium-induced liver injury in literature[J].Drug Evaluation Research,2021,44(7):1508-1512.
[4]LI Y,XU X L,LIU Y,et al.Sirolimus-induced adverse reactions in children:a literature analysis[J].Clinical Medication Journal,2021,19(9):74-78.
[5]CHEN J Y,MA J,TONG G L,et al.Literature analysis of lung injury induced by oxaliplatin[J].Chinese Journal of Hospital Pharmacy,2021,41(10):1059-1063.
[6]CHEN J S.《 Chinese Journal of New Drugs 》 1998－2002 Comprehensive analysis of adverse drug reaction reports[J].Chinese Journal of New Drugs,2003,12(12):1046-1047.
[7]Circular of the State Drug Administration on Issuing the guiding principles for the collection and reporting of individual adverse drug reactions[EB/OL].[2018-12-19].https://www.cdr-adr.org.cn/drug_1/zcfg_1/zcfg_zdyz/202009/t20200924_47831.html.
[8]Adverse Drug Reactions Database[Z].2019-07-29.
[9]CANETE-SIFUENTES L,MONROY R,MEDINA-PEREZ MA.A Review and Experimental Comparison of Multivariate Decision Trees[J].IEEE Access,2021,PP(99):1.
[10]KE B,KHANDELWAL M,ASTERIS P G,et al.Rock-burst occurrence prediction based on optimized Nave Bayes models[J].IEEE Access,2021,PP(99):1.
[11]ABDELSALAM M M,ZAHRAN M A.A novel approach ofDiabetic Retinopathy early detection based on Multifractal Geometry Analysis for OCTA Macular Images using Support Vector Machine[J].IEEE Access,2021,PP(99):1.
[12]JALAL A,AHMED A,RAFIQUE A A,et al.Scene Semantic Recognition Based on Modified Fuzzy C-Mean and Maximum Entropy Using Object-to-Object Relations[J].IEEE Access,2021,9(99):27758-27772.
[13]CHEN K L,LU G,LI C W,et al.Obstructed Nearest Neighbor Query Under Uncertainty in the Internet of Things Environment[J].IEEE Access,2021,PP(99):1-1.
[14]ZHANG W J,JIANG L X,ZHANG H,et al.A Two-LayerBayes Model:Random Forest Naive Bayes[J].Journal of Computer Research and Development,2021,58(9):2040-2051.
[15]WANG S W,XU F,CHAO H T,et al.Research on fault classification of textile hot rolling mill based on support vector machine[J].Modern Manufacturing Engineering,2021(6):116-121.
[16]JIE L,JIN T,PAN K,et al.An improved KNN text classification algorithm based on Simhash[C]//2017 IEEE 16th International Conference on Cognitive Informatics & Cognitive Computing(ICCICC),2017.
[17]ALSALEH D,LARABI-MARIE-SAINTE S.Arabic TextClassification using Convolutional Neural Network and Genetic Algorithms[J].IEEE Access,2021,PP(99):1-1.
[18]WU Z Y,BAI K L,YANG L R,et al.Review on Text Mining of Electronic Medical Record[J].Journal of Computer Research and Development,2021,58(3):513-527.
[19]TURNER C A,JACOBS A D,MARQUES C K,et al.Word2Vec inversion and traditional text classifiers for phenotyping lupus[J].Bmc Medical Informatics & Decision Making,2017,17(1):126.
[20]ZHANG B,SUN Y,LI M Y,et al.Medical Text Classification Based on Transfer Learning and Deep Learning[J].Journal of Shanxi University(Natural Science Edition),2020,43(4):947-954.
[21]ZHOU Y C,CUI Z F,FAN S P,et al.Deep-learning-based biomedical text classification[J].Chinese Journal of Medical Library and Information Science,2019,28(11):1-10
[22]YE H,ZHOU Y R,CAO D,et al.Intelligent Classification of Medical History in Chinese Medical Records Based on Deep Learning[J].China Digital Medicine,2019,14(3):41-43.
[23]HUANG L,DU C S.Application of recurrent neural networks in text classification[J].Journal of Beijing University of Chemical Technology(Natural Science Edition),2017,44(1):98-104.
[24]LUO J,CHEN L F.Sentiment classification of incomplete data based on bidirectional encoder representations from transfor-mers[J].Journal of Computer Applications.
[25]CHEN J,MA J,LI X F.A Short Text Classification MethodBased on the Fused Text Features of Pre-trained Models[J].Data Analysis and Knowledge Discovery,2021,5(9):21-30.
[26]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding[J].arXiv.1810.04805,2018.
[27]VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[J].arXiv.1706.03762,2017.
[28]ZHANG H,JIA T Y,LUO F,et al.Study on Predicting Psychological Traits of Online Text by BERT[J].Journal of Frontiers of Computer Science and Technology,2021,15(8):10.
[29]YANG P,DONG W Y.Chinese Named Entity RecognitionMethod Based on BERT Embedding[J].Computer Engineering,2020,46(4):40-45,52.
[30]SHAO Y F,LI H R,GU J H,et al.Extraction of causal relations based on SBEL and BERT model[J].Database The Journal of Biological Databases and Curation,2021.DOI:10.1093/database/baab005.
[31]WANG Y,CHEN Y R,HAN Z L,et al.Short-Term WindSpeed Forecasting Model Based on Mutual Information and Recursive Neural Network[J].Journal of Shanghai Jiao Tong University,2021,55(9):1080-1086.
[32]ZHOU S Y,FU R,LI J.Zeus at HASOC 2020:Hate speech detection based on ALBERT-DPCNN[J].FIRE (Working Notes),2020:195-201.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于BERT和CNN的药物不良反应个例报道文献分类方法

Literature Classification of Individual Reports of Adverse Drug Reactions Based on BERT and CNN

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

Metrics

本文评价

推荐阅读 0