| 基于深度学习的患者安全事件的命名实体识别 |
| |
| 引用本文： | 周亮杰,马敬东.基于深度学习的患者安全事件的命名实体识别[J].中华医学图书情报杂志,2020,29(6):1-6. |
| |
| 作者姓名： | 周亮杰 马敬东 |
| |
| 作者单位： | 华中科技大学同济医学院，湖北 武汉 430030 |
| |
| 基金项目： | 国家自然科学基金资助项目“互联网医疗环境下慢病服务互动价值形成机制与价值融合模式研究”（71974065） |
| |
| 摘 要： | 为解决日益增长的数据体量与实际作业效率和成本的矛盾，用科学的标注体系对患者安全事件语料进行标注，设计了一种基于深度学习的BERT-BiLSTM-CRF模型，结合中文文本语料的语义特征和字符特征对其进行命名实体识别，最终实验F1值为91.49%，相较于BiLSTM-CRF模型和IDCNN-CRF模型，实体的识别性能分别提升了7.33%和8.30%，验证了该模型的有效性。
|
| 关 键 词： | 患者安全事件 命名实体识别 深度学习 |
| 收稿时间： | 2020/5/14 0:00:00 |
Named entity recognition of patient safety events based on deep learning |
| |
| ZHOU Liang-jie,MA Jing-dong.Named entity recognition of patient safety events based on deep learning[J].Chinese Journal of Medical Library and Information Science,2020,29(6):1-6. |
| |
| Authors: | ZHOU Liang-jie MA Jing-dong |
| |
| Institution: | Central China University of Science and Technology Tongji Medical College, Wuhan 430030, Hubei Province, China |
| |
| Abstract: | A deep learning-based Bert-BiLSTM-CRF model was designed by annotating the patient safety events-related language corpus features using the scientific annotation system in order to solve the contradictions of the increasing data volume with the actual operation efficiency and cost. The named entity was recognized using this model in combination with the semantic features and character features of Chinese text, which showed that the F1 value was 91.49%. The recognition performance of this model increased 7.33% and 8.30% respectively than that of Bert-BiLSTM-CRF model and IDCNN-CRF model, thus verified the efficiency of this model. |
| |
| Keywords: | Patient safety events Named entity identification Deep learning |
|
| 点击此处可从《中华医学图书情报杂志》浏览原始摘要信息 |
| 点击此处可从《中华医学图书情报杂志》下载免费的PDF全文 |
