Enhancing unsupervised medical entity linking with multi-instance learning.

Journal: BMC medical informatics and decision making
Published Date: Nov 16, 2021

Abstract

BACKGROUND: A lot of medical mentions can be extracted from a huge amount of medical texts. In order to make use of these medical mentions, a prerequisite step is to link those medical mentions to a medical domain knowledge base (KB). This linkage of mention to a well-defined, unambiguous KB is a necessary part of the downstream application such as disease diagnosis and prescription of drugs. Such demand becomes more urgent in colloquial and informal situations like online medical consultation, where the medical language is more casual and vaguer. In this article, we propose an unsupervised method to link the Chinese medical symptom mentions to the ICD10 classification in a colloquial background.

Authors

  • Cheng Yan
    Department of Biochemistry and Molecular Medicine, George Washington University, Washington, DC 20037, USA, Institute for Genome Sciences, University of Maryland School of Medicine, Baltimore, MD 21201, USA, Center for Bioinformatics and Information Technology, National Cancer Institute, 9609 Medical Center Drive, Rockville, MD 20892-9760, USA, NASA Jet Propulsion Laboratory, Pasadena, CA, USA, Division of Cancer Prevention, National Cancer Institute, 9609 Medical Center Drive, Rockville, MD 20892-9760, USA, Wellcome Trust Sanger Institute, Cambridge, UK and McCormick Genomic and Proteomic Center, George Washington University, Washington, DC 20037, USA.
  • Yuanzhe Zhang
    National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China. yzzhang@nlpr.ia.ac.cn.
  • Kang Liu
    Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, 100094, China. liukang@csu.ac.cn.
  • Jun Zhao
  • Yafei Shi
    Unisound AI Technology Co., Ltd., Beijing, China.
  • Shengping Liu
    Unisound AI Technology Co., Ltd., Beijing, China.

Keywords

External Resources

Popular Topics
Recent Journals