| 基于预训练模型的药物不良事件抽取方法研究 |
| 修订日期：2023-08-05 点此下载全文 |
| 引用本文：袁驰,李计巧,王正瑶,等.基于预训练模型的药物不良事件抽取方法研究[J].医学信息学杂志,2024,45(2):38-43 |
| 摘要点击次数: |
| 全文下载次数: |
|
| 基金项目:国家自然科学基金项目(项目编号:62302151)；中央高校基本科研业务费(项目编号:B220202076,B220201032)。 |
|
| 中文摘要:目的/意义 研究医学文本药物不良事件数据抽取方法,为临床用药风险管理和科学决策提供支持。方法/过程 基于预训练模型,结合实体识别和关系抽取两个子任务的关联性,设计面向药物不良事件监测的实体关系联合抽取方法。结果/结论 在公开药物不良事件抽取数据集上的实验表明,该方法优于已有方法,能够有效地从医学文本中提取药物不良事件信息及其关系,为药物不良事件的发现与监测提供有力手段。 |
| 中文关键词:药物不良事件 实体关系抽取 预训练模型 自然语言处理 医学 |
| |
| A Pre-trained Language Model-based Method for Adverse Drug Events Extraction |
|
|
| Abstract:Significance To study the extraction method of adverse drug event (ADE) data from medical texts, and to provide support for clinical drug risk management and scientific decision-making. Method/Process Based on pre-trained model, by combining 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. |
| keywords:adverse drug event entity relation extraction pre-trained model natural language processing medicine |
| 查看全文 查看/发表评论 下载PDF阅读器 |
|
|
|
