Classifying patient portal messages using Convolutional Neural Networks.

Journal: Journal of biomedical informatics
Published Date: Aug 30, 2017

Abstract

OBJECTIVE: Patients communicate with healthcare providers via secure messaging in patient portals. As patient portal adoption increases, growing messaging volumes may overwhelm providers. Prior research has demonstrated promise in automating classification of patient portal messages into communication types to support message triage or answering. This paper examines if using semantic features and word context improves portal message classification.

Authors

  • Lina Sulieman
    Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA. Electronic address: lina.m.sulieman@vanderbilt.edu.
  • David Gilmore
    Department of Biological Sciences, College of Science and Mathematics, Arkansas State University, Jonesboro, AR 72467, United States.
  • Christi French
    Digital Reasoning Systems, Inc., Nashville, TN, USA.
  • Robert M Cronin
    Vanderbilt University Medical Center, Nashville, Tennessee.
  • Gretchen Purcell Jackson
    Vanderbilt University Medical Center, Nashville, Tennessee.
  • Matthew Russell
    Digital Reasoning Systems, Inc., Nashville, TN, USA.
  • Daniel Fabbri
    Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, Tennessee, United States of America.

Keywords

External Resources

Popular Topics
Recent Journals