Machine learning for real-time prediction of complications in critical care: a retrospective study.

Journal: The Lancet. Respiratory medicine
Published Date: Dec 1, 2018

Abstract

BACKGROUND: The large amount of clinical signals in intensive care units can easily overwhelm health-care personnel and can lead to treatment delays, suboptimal care, or clinical errors. The aim of this study was to apply deep machine learning methods to predict severe complications during critical care in real time after cardiothoracic surgery.

Authors

  • Alexander Meyer
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany; Berlin Institute of Health, Berlin, Germany. Electronic address: meyera@dhzb.de.
  • Dina Zverinski
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; Department of Computer Science, ETH Zurich, Zurich, Switzerland.
  • Boris Pfahringer
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; Berlin Institute of Health, Berlin, Germany.
  • Jörg Kempfert
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany.
  • Titus Kuehne
    Institute of Imaging Science and Computational Modelling, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Simon H Sündermann
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; Department of Cardiovascular Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Christof Stamm
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; Berlin Center for Regenerative Therapies, Charité - Universitätsmedizin Berlin, Berlin, Germany; DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany.
  • Thomas Hofmann
    Department of Computer Science, ETH Zurich, Zurich, Switzerland.
  • Volkmar Falk
    Department of Cardiothoracic and Vascular Surgery, Deutsches Herzzentrum Berlin, Berlin, Germany; DZHK (German Centre for Cardiovascular Research), Berlin, Germany; Department of Cardiothoracic Surgery, Charité - Universitätsmedizin Berlin, Berlin, Germany.
  • Carsten Eickhoff
    Department of Computer Science, ETH Zurich, Zurich, Switzerland; Center for Biomedical Informatics, Brown University, Providence, RI, USA.

Keywords

External Resources

Popular Topics
Recent Journals