Simplifying radiologic reports with natural language processing: a novel approach using ChatGPT in enhancing patient understanding of MRI results.

Journal: Archives of orthopaedic and trauma surgery
Published Date:

Abstract

PURPOSE: The aim of this prospective cohort study was to assess the factual accuracy, completeness of medical information, and potential harmfulness of incorrect conclusions by medical professionals in automatically generated texts of varying complexity (1) using ChatGPT, Furthermore, patients without a medical background were asked to evaluate comprehensibility, information density, and conclusion possibilities (2).

Authors

  • Sebastian Schmidt
    Institute of Management for Medicine and Health Sciences, University of Bayreuth, Prieserstr. 2, Bayreuth, 95444, Germany.
  • Alexander Zimmerer
    Department of Orthopaedic and Trauma Surgery, Orthopädische Klinik Paulinenhilfe, Diakonieklinikum, Rosenbergstrasse 38, 70192, Stuttgart, Germany.
  • Tudor Cucos
    Department of Radiology, ViDia Christliche Kliniken Karlsruhe, Steinhäuser Straße 18, 76135, Karlsruhe, Germany.
  • Matthias Feucht
    Department of Orthopaedic and Trauma Surgery, Orthopädische Klinik Paulinenhilfe, Diakonieklinikum, Rosenbergstrasse 38, 70192, Stuttgart, Germany.
  • Luis Navas
    Department of Orthopaedic and Trauma Surgery, Orthopädische Klinik Paulinenhilfe, Diakonieklinikum, Rosenbergstrasse 38, 70192, Stuttgart, Germany.