Machine learning-based prediction of transfusion.

Journal: Transfusion
PMID: 32596877

Abstract

BACKGROUND: The ability to predict transfusions arising during hospital admission might enable economized blood supply management and might furthermore increase patient safety by ensuring a sufficient stock of red blood cells (RBCs) for a specific patient. We therefore investigated the precision of four different machine learning-based prediction algorithms to predict transfusion, massive transfusion, and the number of transfusions in patients admitted to a hospital.

Authors

  • Andreas Mitterecker
    Institute for Machine Learning, Johannes Kepler University, Linz, Austria.
  • Axel Hofmann
    Department of Anesthesiology and Critical Care Medicine, University and University Hospital, Zürich, Switzerland.
  • Kevin M Trentino
    Data and Digital Innovation, East Metropolitan Health Service, Perth, Australia.
  • Adam Lloyd
    Data and Digital Innovation, East Metropolitan Health Service, Perth, Australia.
  • Michael F Leahy
    Department of Haematology, PathWest Laboratory Medicine, Royal Perth Hospital, Perth, Australia.
  • Karin Schwarzbauer
    Institute for Machine Learning, Johannes Kepler University, Linz, Austria.
  • Thomas Tschoellitsch
    Department of Anesthesiology and Critical Care Medicine, Kepler University Hospital GmbH and Johannes Kepler University, Linz, Austria.
  • Carl Böck
    Department of Anesthesiology and Critical Care Medicine, Kepler University Hospital GmbH and Johannes Kepler University, Linz, Austria.
  • Sepp Hochreiter
    Institute for Machine Learning Johannes Kepler University Linz Austria.
  • Jens Meier
    Department of Anesthesiology and Intensive Care Medicine, Faculty of Medicine of the Kepler University Linz, Krankenhausstraße 9, 4020 Linz, Austria. Electronic address: jens.meier@gmail.com.

Keywords

External Resources

Popular Topics
Recent Journals