Research on textual classification of medical history in electronic patient records based on LSTM

Yirong Zhuo; Dong Cao; Haimei Wu; Hui Ye

doi:10.1117/12.2550681

27 November 2019 Research on textual classification of medical history in electronic patient records based on LSTM

Yirong Zhuo, Dong Cao, Haimei Wu, Hui Ye

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113212H (2019) https://doi.org/10.1117/12.2550681
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

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.

Citation Download Citation

Yirong Zhuo, Dong Cao, Haimei Wu, and Hui Ye "Research on textual classification of medical history in electronic patient records based on LSTM", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212H (27 November 2019); https://doi.org/10.1117/12.2550681

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