GPT-4 for automated sequence-level determination of MRI protocols based on radiology request forms from clinical routine.

Journal: European radiology
Published Date:

Abstract

OBJECTIVES: This study evaluated GPT-4's accuracy in MRI sequence selection based on radiology request forms (RRFs), comparing its performance to radiology residents.

Authors

  • Robert Terzis
    Department of Diagnostic and Interventional Radiology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
  • Kenan Kaya
    Department of Diagnostic and Interventional Radiology University Hospital Cologne Cologne Germany.
  • Thomas Schömig
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
  • Jan Paul Janssen
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany. jan.janssen@uk-koeln.de.
  • Andra-Iza Iuga
    Institute for Diagnostic and Interventional Radiology, University Cologne, Faculty of Medicine and University Hospital Cologne, Kerpener Straße 62, 50937, Cologne, Germany. Electronic address: andra.iuga@uk-koeln.de.
  • Jonathan Kottlors
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
  • Simon Lennartz
    Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional Radiology, University of Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
  • Carsten Gietzen
    From the Department of Neurology (H.G., M.H.T.S., C.W., J.D., N.R., G.R.F., O.A.O.), Faculty of Medicine and University Hospital Cologne; Division of Cardiology, Pneumology, Angiology and Intensive Care (C.A., S. Baldus), Department of Internal Medicine III, University of Cologne; Department of Neurology (S. Bittner), University Medical Center Mainz; Cognitive Neuroscience (N.R., O.A.O.), Institute of Neuroscience and Medicine (INM-3), Research Center Jülich; and Institute for Diagnostic and Interventional Radiology (C.Z., C.G., M.S.), Faculty of Medicine and University Hospital Cologne, University of Cologne, Germany.
  • Cansin Gözdas
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Cologne, Germany.
  • Lukas Müller
    Klinik und Poliklinik für Diagnostische und Interventionelle Radiologie, Universitätsmedizin Mainz, Langenbeckstr. 1, 55131, Mainz, Deutschland. lukas.mueller@unimedizin-mainz.de.
  • Robert Hahnfeldt
    Department of Diagnostic and Interventional Radiology, University of Cologne, Faculty of Medicine and University Hospital Cologne, Kerpener Str. 62, 50937, Cologne, Germany.
  • David Maintz
    Institute for Diagnostic and Interventional Radiology, University Hospital Cologne, Cologne, Germany.
  • Thomas Dratsch
    Institute of Diagnostic and Interventional Radiology, University Hospital Cologne, Kerpener Str. 62, 50937, Cologne, Germany. t.dratsch@mac.comn.
  • Lenhard Pennig
    Institute for Diagnostic and Interventional Radiology, Faculty of Medicine and University Hospital Cologne, University of Cologne, Kerpener Straße 62, 50937, Cologne, Germany.

Keywords

No keywords available for this article.