Incorporating medical code descriptions for diagnosis prediction in healthcare.

Journal: BMC medical informatics and decision making
PMID:

Abstract

BACKGROUND: Diagnosis aims to predict the future health status of patients according to their historical electronic health records (EHR), which is an important yet challenging task in healthcare informatics. Existing diagnosis prediction approaches mainly employ recurrent neural networks (RNN) with attention mechanisms to make predictions. However, these approaches ignore the importance of code descriptions, i.e., the medical definitions of diagnosis codes. We believe that taking diagnosis code descriptions into account can help the state-of-the-art models not only to learn meaning code representations, but also to improve the predictive performance, especially when the EHR data are insufficient.

Authors

  • Fenglong Ma
    Department of Computer Science and Engineering, University at Buffalo, NY, USA.
  • Yaqing Wang
    University at Buffalo, Buffalo, NY, USA.
  • Houping Xiao
    Georgia State University, Atlanta, GA, USA.
  • Ye Yuan
    School of Artificial Intelligence and Automation, MOE Key Lab of Intelligent Control and Image Processing, Huazhong University of Science and Technology, Wuhan 430074, China.
  • Radha Chitta
    Kira Systems, Toronto, ON, Canada.
  • Jing Zhou
  • Jing Gao
    Department of Gastroenterology 3, Hubei University of Medicine, Renmin Hospital, Shiyan, Hubei, China.