Research on text classification of traditional Chinese medicine medical 
records with ERNIE model

Feng Yuan; Chengzhi Duan

doi:10.1117/12.2660110

6 December 2022 Research on text classification of traditional Chinese medicine medical records with ERNIE model

Feng Yuan, Chengzhi Duan

Proceedings Volume 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022); 1245845 (2022) https://doi.org/10.1117/12.2660110
Event: International Conference on Biomedical and Intelligent Systems, 2022, Chengdu, China

Abstract

Text classification is one of the basic tasks of text mining. In the medical field, a lot of research has been conducted on text classification of English clinical notes of modern medicine. This paper studies the classification of common diseases in than that of BERT_CNN model, indicating that the Traditional Chinese Medicine(TCM) clinical records based on actual data. We explored many of the most advanced deep learning models and found recent advances in Enhanced Representation through Knowledge Integration(ERNIE) models can achieve better results than other deep learning models and other state-of-the-art methods. First, ERNIE model is used to obtain more fully semantic distributed text representation. Then, the deep convolutional neural network is introduced to further extract the encoding features of context to obtain deeper text feature representation. Finally, a classifier (Soft Maximum, Softmax) is used to classify common diseases. Based on a large number of medical case data sets obtained from a hospital, the comparison experiment of multiple groups shows that the F1 value is 3.2% higher than BERT_CNN model, and the accuracy rate is 4.4% higher than BERT_CNN model, and the accuracy rate is 0.7539. The results show that the TCM text classification method based on ERNIE model can effectively improve the performance of Chinese text classification.

Citation Download Citation

Feng Yuan and Chengzhi Duan "Research on text classification of traditional Chinese medicine medical records with ERNIE model", Proc. SPIE 12458, International Conference on Biomedical and Intelligent Systems (IC-BIS 2022), 1245845 (6 December 2022); https://doi.org/10.1117/12.2660110

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Data modeling

Medicine

Performance modeling

Computer programming

Head

Medical research

Classification systems

Show All Keywords

Keywords/Phrases

Search In:

Publication Years