From open-ended to multiple-choice: evaluating diagnostic performance and consistency of ChatGPT, Google Gemini and Claude AI.

Journal: Wiadomosci lekarskie (Warsaw, Poland : 1960)
PMID: 39661873

Abstract

OBJECTIVE: Aim: To determine the performance and response repeatability of freely available LLMs in diagnosing diseases based on clinical case descriptions.

Authors

  • Yaroslav O Mykhalko
    UZHHOROD NATIONAL UNIVERSITY, UZHHOROD, UKRAINE.
  • Yaroslav F Filak
    UZHHOROD NATIONAL UNIVERSITY, UZHHOROD, UKRAINE.
  • Yuliia V Dutkevych-Ivanska
    UZHHOROD NATIONAL UNIVERSITY, UZHHOROD, UKRAINE.
  • Mariana V Sabadosh
    UZHHOROD NATIONAL UNIVERSITY, UZHHOROD, UKRAINE.
  • Yelyzaveta I Rubtsova
    UZHHOROD NATIONAL UNIVERSITY, UZHHOROD, UKRAINE.

Keywords

External Resources

Popular Topics
Recent Journals