Natural language processing and machine learning to identify alcohol misuse from the electronic health record in trauma patients: development and internal validation.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date: Mar 1, 2019

Abstract

OBJECTIVE: Alcohol misuse is present in over a quarter of trauma patients. Information in the clinical notes of the electronic health record of trauma patients may be used for phenotyping tasks with natural language processing (NLP) and supervised machine learning. The objective of this study is to train and validate an NLP classifier for identifying patients with alcohol misuse.

Authors

  • Majid Afshar
    Loyola University Chicago, Chicago, IL.
  • Andrew Phillips
    Department of Computer Science, Loyola University, Chicago, Illinois, USA.
  • Niranjan Karnik
    Department of Psychiatry, Rush University Medical Center, Chicago, Illinois, USA.
  • Jeanne Mueller
    Department of Surgery, Loyola University Medical Center, Maywood, Illinois, USA.
  • Daniel To
    Health Sciences Division, Burn and Shock Trauma Research Institute, Stritch School of Medicine, Loyola University, Maywood, Illinois, USA.
  • Richard Gonzalez
    Department of Surgery, Loyola University Medical Center, Maywood, Illinois, USA.
  • Ron Price
    Informatics and Systems Development, Health Sciences Division, Loyola University Chicago, Maywood, IL.
  • Richard Cooper
    Department of Computer Science, Loyola University, Chicago, Illinois, USA.
  • Cara Joyce
    Loyola University Chicago, Chicago, IL.
  • Dmitriy Dligach
    Department of Public Health Sciences, Stritch School of Medicine, Loyola University Chicago, Maywood, IL.

Keywords

External Resources

Popular Topics
Recent Journals