Abstract
The electronic medical record (EMR) is a patient’s individual medical record written by health care providers to describe the medical activities of patients. Named entity recognition (NER) of EMR is helpful to extract important information from a large number of unstructured texts, which lays a foundation for medical data mining and application. The named entity of Traditional Chinese Medicine (TCM) is more complex and its length is uncertain. In order to explore the effective method of named entity recognition of TCM EMR, after comparing the existing entity recognition methods and models, this paper selects three models, BiLSTM-CRF, lattice LSTM-CRF and BERT, to recognize the symptom entities in EMR, and carries out comparative experiments. After the real EMR data was manually labeled, three models were used to train, and the precision, recall and F1 value were used to evaluate the recognition effect of the model. The experimental results show that BERT model has the best recognition effect about TCM EMR, the precision is 89.94%, the recall is 88.27%, and the F1 value is 89.10%.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Li, B., Kang, X., et al.: Named entity recognition in Chinese electronic medical records using Transformer-CRF. Comput. Eng. Appl. 56(5), 153–159 (2020)
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., Dyer, C.: Neural architectures for named entity recognition. In: Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 260–270 (2016)
Sun, C., Xie, Q.: Discussion on methods of terminology recognition in TCM medical records. Chin. J. Libr. Inf. Sci. Tradit. Chin. Med. 44(2), 1–5 (2020)
Li, M., Liu, Z., Yao, Y.: LSTM-CRF based symptom term recognition on traditional Chinese medical case. J. Comput. Appl. 38(S2), 42–46 (2018)
Gao, S., Jin, P., Zhang, D.: Research on named entity recognition of TCM classics based on deep learning. Technol. Intell. Eng. 5(01), 113–123 (2019)
Zhang, Y., Guan, B., et al.: Study on the entity extraction of traditional Chinese medicine on the basis of deep learning. J. Med. Inform. 40(02), 58–63 (2019)
Zhang, Y., Yang, J.: Chinese NER using lattice LSTM. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pp. 1554–1564 (2018)
Devlin, J., Chang, M., Lee, K., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4171–4186 (2019)
Pan, C., Wang, Q., et al.: Chinese electronic medical record named entity recognition based on sentence-level lattice-long short-term memory neural network. Acad. J. Second Mil. Med. Univ. 40(05), 497–506 (2019)
Acknowledgements
This study was supported by the Health Commission of Hubei Province Guiding Project (#WJ2019F185).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lin, F., Xie, D. (2020). Research on Named Entity Recognition of Traditional Chinese Medicine Electronic Medical Records. In: Huang, Z., Siuly, S., Wang, H., Zhou, R., Zhang, Y. (eds) Health Information Science. HIS 2020. Lecture Notes in Computer Science(), vol 12435. Springer, Cham. https://doi.org/10.1007/978-3-030-61951-0_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-61951-0_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61950-3
Online ISBN: 978-3-030-61951-0
eBook Packages: Computer ScienceComputer Science (R0)