Five advanced chatbots solving European Diploma in Radiology (EDiR) text-based questions: differences in performance and consistency.

Journal: European radiology experimental
Published Date:

Abstract

BACKGROUND: We compared the performance, confidence, and response consistency of five chatbots powered by large language models in solving European Diploma in Radiology (EDiR) text-based multiple-response questions.

Authors

  • Jakub Pristoupil
    Department of Imaging Methods, Motol University Hospital and Second Faculty of Medicine, Charles University, Prague, Czech Republic.
  • Laura Oleaga
    Department of Radiology, Clinical Diagnostic Imaging Centre, Hospital Clínic de Barcelona, Barcelona, Spain.
  • Vanesa Junquero
    Department of Radiology, Clinical Diagnostic Imaging Centre, Hospital Clínic de Barcelona, Barcelona, Spain.
  • Cristina Merino
    Department of Radiology, Clinical Diagnostic Imaging Centre, Hospital Clínic de Barcelona, Barcelona, Spain.
  • Süha Süreyya Özbek
    Department of Radiology, Ege University Faculty of Medicine, İzmir, Turkey
  • Lukas Lambert
    Department of Imaging Methods, Motol University Hospital and Second Faculty of Medicine, Charles University, Prague, Czech Republic. lambert.lukas@gmail.com.