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
孟祥福 1任全莹 1杨东燊 1李可千 2姚克宇 3朱彦3
作者信息
- 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
- 折叠
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.
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 informa-tion.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 algo-rithm,through the comparison experiment of text classification technology,an efficient and fast classification method for the liter-ature data of adverse drug reactions case reports is established,and then the types of adverse drug reactions are distinguished.Ex-perimental 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.
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/BERTKey words
Adverse drug reactions/Individual case literature report/Medical text classification/Deep learning/BERT引用本文复制引用
基金项目
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(ZZ13-YQ-126)
中央级公益性科研院所基本科研业务费专项(ZZ150314)
出版年
2024
NETL
NSTL
万方数据