KETOS: Clinical decision support and machine learning as a service - A training and deployment platform based on Docker, OMOP-CDM, and FHIR Web Services.

Journal: PloS one
PMID: 31581246

Abstract

BACKGROUND AND OBJECTIVE: To take full advantage of decision support, machine learning, and patient-level prediction models, it is important that models are not only created, but also deployed in a clinical setting. The KETOS platform demonstrated in this work implements a tool for researchers allowing them to perform statistical analyses and deploy resulting models in a secure environment.

Authors

  • Julian Gruendner
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Thorsten Schwachhofer
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Phillip Sippl
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Nicolas Wolf
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Marcel Erpenbeck
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Christian Gulden
    Chair of Medical Informatics, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Lorenz A Kapsner
    Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany.
  • Jakob Zierk
    Medical Centre for Information and Communication Technology, Universitätsklinikum Erlangen, Erlangen, Germany.
  • Sebastian Mate
    Institute for Medical Informatics, University Erlangen-Nuremberg, Erlangen, Germany.
  • Michael Stürzl
    Division of Molecular and Experimental Surgery, Department of Surgery, Friedrich-Alexander University, Erlangen-Nürnberg , Erlangen, Germany.
  • Roland Croner
    Department of General, Visceral, Vascular and Graft Surgery, University Hospital, Magdeburg, Germany.
  • Hans-Ulrich Prokosch
    Institute for Medical Informatics, University Erlangen-Nuremberg, Erlangen, Germany; Center for Medical Information and Communication, Erlangen University Hospital, Erlangen, Germany.
  • Dennis Toddenroth
    Institute for Medical Informatics, University Erlangen-Nuremberg, Erlangen, Germany.

Keywords

External Resources

Popular Topics
Recent Journals