Comparative ranking of marginal confounding impact of natural language processing-derived versus structured features in pharmacoepidemiology.

Journal: Computers in biology and medicine
PMID:

Abstract

OBJECTIVE: To explore the ability of natural language processing (NLP) methods to identify confounder information beyond what can be identified using claims codes alone for pharmacoepidemiology.

Authors

  • Joseph M Plasek
    Division of General Internal Medicine and Primary Care, Brigham and Women's Hospital, Boston, Massachusetts.
  • Richard D Wyss
    Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
  • Janick G Weberpals
    Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
  • Jie Yang
    Key Laboratory of Development and Maternal and Child Diseases of Sichuan Province, Department of Pediatrics, Sichuan University, Chengdu, China.
  • Thomas DeRamus
    Tri-Institutional Center for Translational Research in Neuroimaging and Data Science (TReNDS), Georgia State University, Georgia Institute of Technology, Emory University, Atlanta, GA, United States of America.
  • Theodore N Tsacogianis
    Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
  • Kerry Ngan
    Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
  • Lily G Bessette
    Department of Medicine, Brigham and Women's Hospital, Boston, MA, United States.
  • Kueiyu Joshua Lin
    Division of Pharmacoepidemiology and Pharmacoeconomics Department of Medicine Brigham and Women's Hospital Harvard Medical School Boston MA.
  • Li Zhou
    School of Education, China West Normal University, Nanchong, Sichuan, China.