Assessment of Machine Learning vs Standard Prediction Rules for Predicting Hospital Readmissions.

Journal: JAMA network open
Published Date:

Abstract

IMPORTANCE: Hospital readmissions are associated with patient harm and expense. Ways to prevent hospital readmissions have focused on identifying patients at greatest risk using prediction scores.

Authors

  • Daniel J Morgan
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Bill Bame
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Paul Zimand
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Patrick Dooley
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Kerri A Thom
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Anthony D Harris
    Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore.
  • Soren Bentzen
    Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore.
  • Walt Ettinger
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • Stacy D Garrett-Ray
    Department of Population Health, University of Maryland Medical System, Baltimore.
  • J Kathleen Tracy
    Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore.
  • Yuanyuan Liang
    Department of Epidemiology and Public Health, University of Maryland School of Medicine, Baltimore.