Share Email Print
cover

Proceedings Paper

Research on textual classification of medical history in electronic patient records based on LSTM
Author(s): Yirong Zhuo; Dong Cao; Haimei Wu; Hui Ye
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Natural Language Processing (NLP) is an important direction in the field of computer science and artificial intelligence. Combining with deep learning, NLP can effectively transform unstructured natural language into structured data. The electronic medical records of hospitals are mainly used in clinic, and the data of electronic medical records need to be reorganized to carry out research. This paper mainly studies the automatic classification and extraction of medical history information fields based on Convolutional neural network (CNN) and Long Short-Term Memory network (LSTM), aiming at solving the problem of traditional Chinese medicine. The classification problem of automatic extraction of all medical history information from mixed text information of medical records. The experimental results show that the F value is 0.8506 based on Convolutional Neural Network (CNN) and 0.8810 based on LSTM, which has good classification effect.

Paper Details

Date Published: 27 November 2019
PDF: 5 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212H (27 November 2019); doi: 10.1117/12.2550681
Show Author Affiliations
Yirong Zhuo, Guangzhou Univ. of Chinese Medicine (China)
Dong Cao, Guangzhou Univ. of Chinese Medicine (China)
Haimei Wu, Guangzhou Univ. of Chinese Medicine (China)
Hui Ye, Guangzhou Univ. of Chinese Medicine (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray