An imConvNet-based deep learning model for Chinese medical named entity recognition
Abstract Background With the development of current medical technology, information management becomes perfect in the medical field. Medical big data analysis is based on a large amount of medical and health data stored in the electronic medical system, such as electronic medical records and medical...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-11-01
|
| Series: | BMC Medical Informatics and Decision Making |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12911-022-02049-4 |
| _version_ | 1811304592839802880 |
|---|---|
| author | Yuchen Zheng Zhenggong Han Yimin Cai Xubo Duan Jiangling Sun Wei Yang Haisong Huang |
| author_facet | Yuchen Zheng Zhenggong Han Yimin Cai Xubo Duan Jiangling Sun Wei Yang Haisong Huang |
| author_sort | Yuchen Zheng |
| collection | DOAJ |
| description | Abstract Background With the development of current medical technology, information management becomes perfect in the medical field. Medical big data analysis is based on a large amount of medical and health data stored in the electronic medical system, such as electronic medical records and medical reports. How to fully exploit the resources of information included in these medical data has always been the subject of research by many scholars. The basis for text mining is named entity recognition (NER), which has its particularities in the medical field, where issues such as inadequate text resources and a large number of professional domain terms continue to face significant challenges in medical NER. Methods We improved the convolutional neural network model (imConvNet) to obtain additional text features. Concurrently, we continue to use the classical Bert pre-training model and BiLSTM model for named entity recognition. We use imConvNet model to extract additional word vector features and improve named entity recognition accuracy. The proposed model, named BERT-imConvNet-BiLSTM-CRF, is composed of four layers: BERT embedding layer—getting word embedding vector; imConvNet layer—capturing the context feature of each character; BiLSTM (Bidirectional Long Short-Term Memory) layer—capturing the long-distance dependencies; CRF (Conditional Random Field) layer—labeling characters based on their features and transfer rules. Results The average F1 score on the public medical data set yidu-s4k reached 91.38% when combined with the classical model; when real electronic medical record text in impacted wisdom teeth is used as the experimental object, the model's F1 score is 93.89%. They all show better results than classical models. Conclusions The suggested novel model (imConvNet) significantly improves the recognition accuracy of Chinese medical named entities and applies to various medical corpora. |
| first_indexed | 2024-04-13T08:10:06Z |
| format | Article |
| id | doaj.art-394bad5ff47245b78fdd2edac201974a |
| institution | Directory Open Access Journal |
| issn | 1472-6947 |
| language | English |
| last_indexed | 2024-04-13T08:10:06Z |
| publishDate | 2022-11-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Informatics and Decision Making |
| spelling | doaj.art-394bad5ff47245b78fdd2edac201974a2022-12-22T02:55:02ZengBMCBMC Medical Informatics and Decision Making1472-69472022-11-0122111210.1186/s12911-022-02049-4An imConvNet-based deep learning model for Chinese medical named entity recognitionYuchen Zheng0Zhenggong Han1Yimin Cai2Xubo Duan3Jiangling Sun4Wei Yang5Haisong Huang6Medical College, Guizhou UniversityKey Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou UniversityMedical College, Guizhou UniversityMedical College, Guizhou UniversityGuiyang Hospital of StomatologyMedical College, Guizhou UniversityKey Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou UniversityAbstract Background With the development of current medical technology, information management becomes perfect in the medical field. Medical big data analysis is based on a large amount of medical and health data stored in the electronic medical system, such as electronic medical records and medical reports. How to fully exploit the resources of information included in these medical data has always been the subject of research by many scholars. The basis for text mining is named entity recognition (NER), which has its particularities in the medical field, where issues such as inadequate text resources and a large number of professional domain terms continue to face significant challenges in medical NER. Methods We improved the convolutional neural network model (imConvNet) to obtain additional text features. Concurrently, we continue to use the classical Bert pre-training model and BiLSTM model for named entity recognition. We use imConvNet model to extract additional word vector features and improve named entity recognition accuracy. The proposed model, named BERT-imConvNet-BiLSTM-CRF, is composed of four layers: BERT embedding layer—getting word embedding vector; imConvNet layer—capturing the context feature of each character; BiLSTM (Bidirectional Long Short-Term Memory) layer—capturing the long-distance dependencies; CRF (Conditional Random Field) layer—labeling characters based on their features and transfer rules. Results The average F1 score on the public medical data set yidu-s4k reached 91.38% when combined with the classical model; when real electronic medical record text in impacted wisdom teeth is used as the experimental object, the model's F1 score is 93.89%. They all show better results than classical models. Conclusions The suggested novel model (imConvNet) significantly improves the recognition accuracy of Chinese medical named entities and applies to various medical corpora.https://doi.org/10.1186/s12911-022-02049-4Named entity recognitionConvolutional neural networkChinese electronic medical recordsBiLSTM-CRFBERT |
| spellingShingle | Yuchen Zheng Zhenggong Han Yimin Cai Xubo Duan Jiangling Sun Wei Yang Haisong Huang An imConvNet-based deep learning model for Chinese medical named entity recognition BMC Medical Informatics and Decision Making Named entity recognition Convolutional neural network Chinese electronic medical records BiLSTM-CRF BERT |
| title | An imConvNet-based deep learning model for Chinese medical named entity recognition |
| title_full | An imConvNet-based deep learning model for Chinese medical named entity recognition |
| title_fullStr | An imConvNet-based deep learning model for Chinese medical named entity recognition |
| title_full_unstemmed | An imConvNet-based deep learning model for Chinese medical named entity recognition |
| title_short | An imConvNet-based deep learning model for Chinese medical named entity recognition |
| title_sort | imconvnet based deep learning model for chinese medical named entity recognition |
| topic | Named entity recognition Convolutional neural network Chinese electronic medical records BiLSTM-CRF BERT |
| url | https://doi.org/10.1186/s12911-022-02049-4 |
| work_keys_str_mv | AT yuchenzheng animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT zhenggonghan animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT yimincai animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT xuboduan animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT jianglingsun animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT weiyang animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT haisonghuang animconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT yuchenzheng imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT zhenggonghan imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT yimincai imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT xuboduan imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT jianglingsun imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT weiyang imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition AT haisonghuang imconvnetbaseddeeplearningmodelforchinesemedicalnamedentityrecognition |