Using Clinical Notes and Natural Language Processing for Automated HIV Risk Assessment.

Journal: Journal of acquired immune deficiency syndromes (1999)
Published Date:

Abstract

OBJECTIVE: Universal HIV screening programs are costly, labor intensive, and often fail to identify high-risk individuals. Automated risk assessment methods that leverage longitudinal electronic health records (EHRs) could catalyze targeted screening programs. Although social and behavioral determinants of health are typically captured in narrative documentation, previous analyses have considered only structured EHR fields. We examined whether natural language processing (NLP) would improve predictive models of HIV diagnosis.

Authors

  • Daniel J Feller
    Columbia University, New York, NY, USA.
  • Jason Zucker
    Columbia University, New York, NY, USA.
  • Michael T Yin
    Columbia University, New York, NY, USA.
  • Peter Gordon
    Columbia University, New York, NY, USA.
  • NoĆ©mie Elhadad
    Biomedical Informatics, Columbia University, New York, NY, USA.