Can ChatGPT and Gemini justify brain CT referrals? A comparative study with human experts and a custom prediction model
Custom prediction model's justification analysis strongly aligns with iGuide and surpasses chatbots. Chatbots incorrectly justified almost one-half of all CT brain referrals. Chatbots have limited performance in justifying ambiguous CT brain referrals. Chatbot performance improved when referrals were detailed and included suspected pathology.
Authors
- Jaka Potočnik (ORCID: https://orcid.org/0000-0002-8353-1215)
- Eric Heffernan
- Ronan P. Killeen (ORCID: https://orcid.org/0000-0002-9231-8133)
- Shane J. Foley (ORCID: https://orcid.org/0000-0002-9478-2802)
- Edel Thomas (ORCID: https://orcid.org/0000-0002-0723-338X)
- D Kearney
Institutions
- University College Dublin (IE)
- Royal Victoria Eye and Ear Hospital (IE)
- Mater Misericordiae University Hospital (IE)
- St. Vincent's University Hospital (IE)
Publication Details
- Journal
- European Radiology Experimental
- Published
- 2025-02-18
- DOI
- https://doi.org/10.1186/s41747-025-00569-y
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62