A Pre-trained Language Model-based Method for Adverse Drug Events Extraction

VernacularTitle:基于预训练模型的药物不良事件抽取方法研究
Author: Chi YUAN ¹ ; Jiqiao LI ; Zhengyao WANG ; Huaiyu WANG
Author Information

1. 河海大学计算机与软件学院南京 211100
Keywords: adverse drug event; entity relation extraction; pre-trained model; natural language processing; medicine
From: Journal of Medical Informatics 2024;45(2):38-43
CountryChina
Language:Chinese
Abstract: Purpose/Significance To study the extraction method of adverse drug event(ADE)data from medical texts,and to pro-vide support for clinical drug risk management and scientific decision-making.Method/Process Based on pre-trained model,by com-bining the correlation between the two subtasks of entity recognition and relation extraction,a entity relation joint extraction method for ADE monitoring is designed.Result/Conclusion Experiments on the published ADE extraction dataset show that the proposed method is superior to existing methods and can effectively extract ADE information and its relation from medical texts,providing a powerful means for the discovery and monitoring of ADE.