Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay.

Journal: Journal of the American Medical Informatics Association : JAMIA
Published Date:

Abstract

OBJECTIVE: Emergency departments (EDs) continue to pursue optimal patient flow without sacrificing quality of care. The speed with which a healthcare provider receives pertinent information, such as results from clinical orders, can impact flow. We seek to determine if clinical ordering behavior can be predicted at triage during an ED visit.

Authors

  • Haley S Hunter-Zinck
    Department of Emergency Services, VA Boston Healthcare System, Boston, Massachusetts, USA.
  • Jordan S Peck
    Center for Performance Improvement, MaineHealth, Portland, Maine, USA.
  • Tania D Strout
    Department of Emergency Medicine, Tufts University School of Medicine, Medford, Massachusetts, USA.
  • Stephan A Gaehde
    Department of Emergency Services, VA Boston Healthcare System, Boston, Massachusetts, USA.