Cargando…

Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN

Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR) can be extracted by Named Entity Recognition (NER). However, limited resources of labeled EMR pose a great challenge for mining medical entity terms. In this study, a novel multitask bi-directional RNN...

Descripción completa

Detalles Bibliográficos
Autores principales: Dong, Xishuang, Chowdhury, Shanta, Qian, Lijun, Li, Xiangfang, Guan, Yi, Yang, Jinfeng, Yu, Qiubin
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6497281/
https://www.ncbi.nlm.nih.gov/pubmed/31048840
http://dx.doi.org/10.1371/journal.pone.0216046
_version_ 1783415442611634176
author Dong, Xishuang
Chowdhury, Shanta
Qian, Lijun
Li, Xiangfang
Guan, Yi
Yang, Jinfeng
Yu, Qiubin
author_facet Dong, Xishuang
Chowdhury, Shanta
Qian, Lijun
Li, Xiangfang
Guan, Yi
Yang, Jinfeng
Yu, Qiubin
author_sort Dong, Xishuang
collection PubMed
description Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR) can be extracted by Named Entity Recognition (NER). However, limited resources of labeled EMR pose a great challenge for mining medical entity terms. In this study, a novel multitask bi-directional RNN model combined with deep transfer learning is proposed as a potential solution of transferring knowledge and data augmentation to enhance NER performance with limited data. The proposed model has been evaluated using micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in the case of discharge datasets. For instance, for the case of discharge summary, the micro average F-score is improved by 2.55% and the overall accuracy is improved by 7.53%. For the case of progress notes, the micro average F-score and the overall accuracy are improved by 1.63% and 5.63%, respectively.
format Online
Article
Text
id pubmed-6497281
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-64972812019-05-17 Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN Dong, Xishuang Chowdhury, Shanta Qian, Lijun Li, Xiangfang Guan, Yi Yang, Jinfeng Yu, Qiubin PLoS One Research Article Specific entity terms such as disease, test, symptom, and genes in Electronic Medical Record (EMR) can be extracted by Named Entity Recognition (NER). However, limited resources of labeled EMR pose a great challenge for mining medical entity terms. In this study, a novel multitask bi-directional RNN model combined with deep transfer learning is proposed as a potential solution of transferring knowledge and data augmentation to enhance NER performance with limited data. The proposed model has been evaluated using micro average F-score, macro average F-score and accuracy. It is observed that the proposed model outperforms the baseline model in the case of discharge datasets. For instance, for the case of discharge summary, the micro average F-score is improved by 2.55% and the overall accuracy is improved by 7.53%. For the case of progress notes, the micro average F-score and the overall accuracy are improved by 1.63% and 5.63%, respectively. Public Library of Science 2019-05-02 /pmc/articles/PMC6497281/ /pubmed/31048840 http://dx.doi.org/10.1371/journal.pone.0216046 Text en © 2019 Dong et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Dong, Xishuang
Chowdhury, Shanta
Qian, Lijun
Li, Xiangfang
Guan, Yi
Yang, Jinfeng
Yu, Qiubin
Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title_full Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title_fullStr Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title_full_unstemmed Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title_short Deep learning for named entity recognition on Chinese electronic medical records: Combining deep transfer learning with multitask bi-directional LSTM RNN
title_sort deep learning for named entity recognition on chinese electronic medical records: combining deep transfer learning with multitask bi-directional lstm rnn
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6497281/
https://www.ncbi.nlm.nih.gov/pubmed/31048840
http://dx.doi.org/10.1371/journal.pone.0216046
work_keys_str_mv AT dongxishuang deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT chowdhuryshanta deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT qianlijun deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT lixiangfang deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT guanyi deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT yangjinfeng deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn
AT yuqiubin deeplearningfornamedentityrecognitiononchineseelectronicmedicalrecordscombiningdeeptransferlearningwithmultitaskbidirectionallstmrnn