Predicting hospital admissions, ICU utilization, and prolonged length of stay among febrile pediatric emergency department patients using incomplete and imbalanced electronic health record (EHR) data strategies.

Journal: International journal of medical informatics
Published Date:

Abstract

OBJECTIVE: Determine the efficacy of commonly used approaches to handling missing and/or imbalanced Electronic Health Record (EHR) data on the performance of predictive models targeting risk of admission, intensive care unit (ICU) use, or prolonged length of stay (PLOS) among presenting febrile pediatric emergency department (ED) patients.

Authors

  • Tom Velez
    Computer Technology Associates, Cardiff, CA.
  • Zara Ibrahim
    3rd Year Pediatric Resident, Center for Genetic Medicine Research, Children's National Research Institute, Children's National Hospital.
  • Kanayo Duru
    Department of Pediatrics, Children's National Hospital, Washington, DC, United States; Brown University, Providence, RI, United States.
  • Dante Velez
    Department of Pediatrics, Children's National Hospital, Washington, DC, United States.
  • Maria Triantafyllou
    3rd Year Pediatric Resident, Center for Genetic Medicine Research, Children's National Research Institute, Children's National Hospital.
  • Kenneth McKinley
    Department of Pediatrics, Children's National Hospital, Washington, DC, United States; George Washington University School of Medicine and Health Sciences, Washington, DC, United States.
  • Pasha Saif
    Virginia Tech Carilion School of Medicine, Roanoke, VA, United States.
  • Panagiotis Kratimenos
    Post-doctoral Fellow, Center for Neuroscience Research, Children's National Research Institute, Children's National Hospital, Washington, DC.
  • Andy Clark
    Department of Philosophy, University of Sussex, Brighton, UK; Department of Informatics, University of Sussex, Brighton, UK; Department of Philosophy, Macquarie University, Sydney, New South Wales, Australia.
  • Ioannis Koutroulis
    Children's National Health System, Washington, DC.