Predicting whether patients in an acute medical unit are physiologically fit-for-discharge using machine learning: A proof-of-concept.

Journal: International journal of medical informatics
PMID: 39167884

Abstract

INTRODUCTION: Delays in discharging patients from Acute Medical Units hamper patient flows throughout the hospital. The decision to discharge a patient is mainly based on the patients' physiological condition, but may vary between physicians. An objective decision-support system based on patients' physiological data may help minimizing unnecessary delays in discharge. The aim of this proof-of-concept study is to assess the feasibility of predicting whether patients in an Acute Medical Unit are physiologically fit-for-discharge using machine learning with commonly available hospital data. Furthermore, this study investigated how long before actual time of discharge from the Acute Medical Unit we could predict discharge fitness. Also, the predictive importance of features extracted from these data was assessed.

Authors

  • S H Garssen
    Health Technology and Services Research, Techmed Centre, Faculty of Behavioural, Management and Social Sciences, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands; Clinical Research Center, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands; Department of Patient Care and Monitoring, Philips Research, High Tech Campus 34, 5656 AE Eindhoven, The Netherlands. Electronic address: sgarssen@rijnstate.nl.
  • C A Vernooij
    Department of Patient Care and Monitoring, Philips Research, High Tech Campus 34, 5656 AE Eindhoven, The Netherlands.
  • N Kant
    Health Technology and Services Research, Techmed Centre, Faculty of Behavioural, Management and Social Sciences, University of Twente, Drienerlolaan 5, 7522 NB Enschede, The Netherlands; Clinical Research Center, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands; Department of Anesthesiology, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands. Electronic address: nkant@rijnstate.nl.
  • M V Koning
    Department of Anesthesiology, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands. Electronic address: mvkoning@rijnstate.nl.
  • F H Bosch
    Department of Internal Medicine, Rijnstate Hospital, Wagnerlaan 55, 6815 AD Arnhem, The Netherlands; Department of Internal Medicine, Radboudumc, Geert Grooteplein Zuid 10, 6525 GA Nijmegen, The Netherlands. Electronic address: fhbosch@rijnstate.nl.
  • C J M Doggen
    Department of Health Technology and Services Research, Technical Medical Centre, Faculty of Behavioral, Management and Social Sciences, University of Twente, Enschede, The Netherlands.
  • B P Veldkamp
    Department of Cognition, Data, and Education, Faculty of Behavioural, Management and Social Sciences, University of Twente, De zul 10, 7522 NJ Enschede, The Netherlands. Electronic address: b.p.veldkamp@utwente.nl.
  • W F J Verhaegh
    Department of Data Science & AI Engineering, Philips, High Tech Campus 33, 5656 AE Eindhoven, The Netherlands.
  • S F Oude Wesselink
    Department of Cognition, Data, and Education, Faculty of Behavioural, Management and Social Sciences, University of Twente, De zul 10, 7522 NJ Enschede, The Netherlands. Electronic address: s.f.oudewesselink@utwente.nl.

Keywords

External Resources

Popular Topics
Recent Journals