Computer Engineering and Applications ›› 2023, Vol. 59 ›› Issue (16): 63-73.DOI: 10.3778/j.issn.1002-8331.2209-0366

• Research Hotspots and Reviews • Previous Articles     Next Articles

Review of Relation Extraction in Electronic Medical Records

WANG Chen, LI Ming, MA Jingang   

  1. College of Intelligence and Information Engineering, Shandong University of Traditional Chinese Medicine, Jinan 250355, China
  • Online:2023-08-15 Published:2023-08-15

电子病历关系抽取综述

王辰,李明,马金刚   

  1. 山东中医药大学 智能与信息工程学院,济南 250355

Abstract: The application of information extraction to electronic medical records has yielded rich research results, enabling the utilization of unstructured biomedical data. Relation extraction is an important subtask of information extraction and a bridge from data to knowledge. This paper provides a detailed classification of relation extraction based on different problems and different solutions of relation extraction. Relevant review tasks and representative datasets in the field of relation extraction for electronic medical records are collated. The progress of the application of relation extraction on electronic medical record texts is reviewed in stages, focusing on the wide application of deep learning methods on relation extraction and the progress of pre-trained models on the task of electronic medical record relation extraction at this stage. Finally, an outlook on the field is provided, highlighting the unresolved issues and future research directions.

Key words: electronic medical records, relation extraction, deep learning, pre-trained model

摘要: 信息抽取在电子病历上的应用取得丰富的研究成果,使得非结构化的生物医学数据得以利用。关系抽取是信息抽取的重要子任务,是从数据转化为知识的桥梁。根据关系抽取存在的不同问题以及不同解决方案,对关系抽取进行详细分类。整理了电子病历关系抽取领域的相关评测任务和具有代表性的数据集。分阶段对关系抽取在电子病历文本上的应用进展进行综述,重点介绍了深度学习方法在关系抽取上的广泛应用,以及现阶段预训练模型在电子病历关系抽取任务上的进展。对该领域进行展望,提出了未解决的问题以及未来的研究方向。

关键词: 电子病历, 关系抽取, 深度学习, 预训练模型