Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation
Abstract BackgroundClinical named entity recognition (CNER) is a fundamental task in natural language processing used to extract named entities from electronic medical record texts. In recent years, with the continuous development of machine learning, deep learning models have...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2024-11-01
|
| Series: | JMIR Medical Informatics |
| Online Access: | https://medinform.jmir.org/2024/1/e60334 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850056846965997568 |
|---|---|
| author | Jian Tang Zikun Huang Hongzhen Xu Hao Zhang Hailing Huang Minqiong Tang Pengsheng Luo Dong Qin |
| author_facet | Jian Tang Zikun Huang Hongzhen Xu Hao Zhang Hailing Huang Minqiong Tang Pengsheng Luo Dong Qin |
| author_sort | Jian Tang |
| collection | DOAJ |
| description |
Abstract
BackgroundClinical named entity recognition (CNER) is a fundamental task in natural language processing used to extract named entities from electronic medical record texts. In recent years, with the continuous development of machine learning, deep learning models have replaced traditional machine learning and template-based methods, becoming widely applied in the CNER field. However, due to the complexity of clinical texts, the diversity and large quantity of named entity types, and the unclear boundaries between different entities, existing advanced methods rely to some extent on annotated databases and the scale of embedded dictionaries.
ObjectiveThis study aims to address the issues of data scarcity and labeling difficulties in CNER tasks by proposing a dataset augmentation algorithm based on proximity word calculation.
MethodsWe propose a Segmentation Synonym Sentence Synthesis (SSSS) algorithm based on neighboring vocabulary, which leverages existing public knowledge without the need for manual expansion of specialized domain dictionaries. Through lexical segmentation, the algorithm replaces new synonymous vocabulary by recombining from vast natural language data, achieving nearby expansion expressions of the dataset. We applied the SSSS algorithm to the Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) + conditional random field (CRF) and RoBERTa + Bidirectional Long Short-Term Memory (BiLSTM) + CRF models and evaluated our models (SSSS + RoBERTa + CRF; SSSS + RoBERTa + BiLSTM + CRF) on the China Conference on Knowledge Graph and Semantic Computing (CCKS) 2017 and 2019 datasets.
ResultsOur experiments demonstrated that the models SSSS + RoBERTa + CRF and SSSS + RoBERTa + BiLSTM + CRF achieved F1F1
ConclusionsThe experimental results indicated that our proposed method successfully expanded the dataset and remarkably improved the performance of the model, effectively addressing the challenges of data acquisition, annotation difficulties, and insufficient model generalization performance. |
| format | Article |
| id | doaj-art-9a3c236e66504fe69c797d41ceb3d8bf |
| institution | DOAJ |
| issn | 2291-9694 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | JMIR Publications |
| record_format | Article |
| series | JMIR Medical Informatics |
| spelling | doaj-art-9a3c236e66504fe69c797d41ceb3d8bf2025-08-20T02:51:35ZengJMIR PublicationsJMIR Medical Informatics2291-96942024-11-0112e60334e6033410.2196/60334Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and ValidationJian Tanghttp://orcid.org/0009-0008-2957-4530Zikun Huanghttp://orcid.org/0009-0004-2431-1265Hongzhen Xuhttp://orcid.org/0009-0008-4632-3389Hao Zhanghttp://orcid.org/0009-0005-8893-1970Hailing Huanghttp://orcid.org/0009-0008-0847-7889Minqiong Tanghttp://orcid.org/0009-0003-3198-6140Pengsheng Luohttp://orcid.org/0009-0007-5369-4674Dong Qinhttp://orcid.org/0009-0007-9264-2076 Abstract BackgroundClinical named entity recognition (CNER) is a fundamental task in natural language processing used to extract named entities from electronic medical record texts. In recent years, with the continuous development of machine learning, deep learning models have replaced traditional machine learning and template-based methods, becoming widely applied in the CNER field. However, due to the complexity of clinical texts, the diversity and large quantity of named entity types, and the unclear boundaries between different entities, existing advanced methods rely to some extent on annotated databases and the scale of embedded dictionaries. ObjectiveThis study aims to address the issues of data scarcity and labeling difficulties in CNER tasks by proposing a dataset augmentation algorithm based on proximity word calculation. MethodsWe propose a Segmentation Synonym Sentence Synthesis (SSSS) algorithm based on neighboring vocabulary, which leverages existing public knowledge without the need for manual expansion of specialized domain dictionaries. Through lexical segmentation, the algorithm replaces new synonymous vocabulary by recombining from vast natural language data, achieving nearby expansion expressions of the dataset. We applied the SSSS algorithm to the Robustly Optimized Bidirectional Encoder Representations from Transformers Pretraining Approach (RoBERTa) + conditional random field (CRF) and RoBERTa + Bidirectional Long Short-Term Memory (BiLSTM) + CRF models and evaluated our models (SSSS + RoBERTa + CRF; SSSS + RoBERTa + BiLSTM + CRF) on the China Conference on Knowledge Graph and Semantic Computing (CCKS) 2017 and 2019 datasets. ResultsOur experiments demonstrated that the models SSSS + RoBERTa + CRF and SSSS + RoBERTa + BiLSTM + CRF achieved F1F1 ConclusionsThe experimental results indicated that our proposed method successfully expanded the dataset and remarkably improved the performance of the model, effectively addressing the challenges of data acquisition, annotation difficulties, and insufficient model generalization performance.https://medinform.jmir.org/2024/1/e60334 |
| spellingShingle | Jian Tang Zikun Huang Hongzhen Xu Hao Zhang Hailing Huang Minqiong Tang Pengsheng Luo Dong Qin Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation JMIR Medical Informatics |
| title | Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation |
| title_full | Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation |
| title_fullStr | Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation |
| title_full_unstemmed | Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation |
| title_short | Chinese Clinical Named Entity Recognition With Segmentation Synonym Sentence Synthesis Mechanism: Algorithm Development and Validation |
| title_sort | chinese clinical named entity recognition with segmentation synonym sentence synthesis mechanism algorithm development and validation |
| url | https://medinform.jmir.org/2024/1/e60334 |
| work_keys_str_mv | AT jiantang chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT zikunhuang chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT hongzhenxu chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT haozhang chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT hailinghuang chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT minqiongtang chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT pengshengluo chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation AT dongqin chineseclinicalnamedentityrecognitionwithsegmentationsynonymsentencesynthesismechanismalgorithmdevelopmentandvalidation |