Protocol for the automatic extraction of epidemiological information via a pre-trained language model

Zhizheng Wang; Xiao Fan Liu; Zhanwei Du; Lin Wang; Ye Wu; Petter Holme; Michael Lachmann; Hongfei Lin; Zhuoyue Wang; Yu Cao; Zoie S Y Wong; Xiao-Ke Xu; Yuanyuan Sun

doi:10.1016/j.xpro.2023.102392

Protocol for the automatic extraction of epidemiological information via a pre-trained language model

STAR Protoc. 2023 Sep 15;4(3):102392. doi: 10.1016/j.xpro.2023.102392. Epub 2023 Jul 1.

Authors

Zhizheng Wang¹, Xiao Fan Liu², Zhanwei Du³, Lin Wang⁴, Ye Wu⁵, Petter Holme⁶, Michael Lachmann⁷, Hongfei Lin¹, Zhuoyue Wang¹, Yu Cao¹, Zoie S Y Wong⁸, Xiao-Ke Xu⁹, Yuanyuan Sun¹⁰

Affiliations

¹ College of Computer Science and Technology, Dalian University of Technology, 116023, Dalian, Liaoning, China.
² Web Mining Laboratory, Department of Media and Communication, City University of Hong Kong, Kowloon Tong, Hong Kong Special Administrative Region, 999077, China.
³ WHO Collaborating Centre for Infectious Disease Epidemiology and Control, School of Public Health, Li Ka Shing Faculty of Medicine, The University of Hong Kong, Central And Western District, Hong Kong Special Administrative Region, 999077, China.
⁴ Department of Genetics, University of Cambridge, Cambridge CB2 3EH, UK.
⁵ Computational Communication Research Center and School of Journalism and Communication, Beijing Normal University, Beijing 100091, China.
⁶ Tokyo Tech World Research Hub Initiative (WRHI), Institute of Innovative Research, Tokyo Institute of Technology, Tokyo 152-8550, Japan.
⁷ Santa Fe Institute, Santa Fe, NM 87507, USA.
⁸ Graduate School of Public Health, St. Luke's International University, Tokyo 104-0044, Japan. Electronic address: zoiesywong@gmail.com.
⁹ Computational Communication Research Center, Beijing Normal University, Zhuhai, Guangdong, 519087, China; School of Journalism and Communication, Beijing Normal University, Beijing, 100875, China. Electronic address: xuxiaoke@foxmail.com.
¹⁰ College of Computer Science and Technology, Dalian University of Technology, 116023, Dalian, Liaoning, China. Electronic address: syuan@dlut.edu.cn.

Abstract

The lack of systems to automatically extract epidemiological fields from open-access COVID-19 cases restricts the timeliness of formulating prevention measures. Here we present a protocol for using CCIE, a COVID-19 Cases Information Extraction system based on the pre-trained language model.¹ We describe steps for preparing supervised training data and executing python scripts for named entity recognition and text category classification. We then detail the use of machine evaluation and manual validation to illustrate the effectiveness of CCIE. For complete details on the use and execution of this protocol, please refer to Wang et al.².

Keywords: Clinical Protocol; Computer Sciences; Health Sciences.

MeSH terms

COVID-19* / epidemiology
Humans
Language
Natural Language Processing*