Generative pre-trained transformer 4o (GPT-4o) in solving text-based multiple response questions for European Diploma in Radiology (EDiR): a comparative study with radiologists
In EDiR text-based questions, ChatGPT-4o scored higher (82%) than EDiR participants (49%). Compared to radiologists, GPT-4o excelled in identifying correct responses. GPT-4o responses demonstrated higher agreement (κ = 0.87) compared to EDiR candidates (κ = 0.33).
Authors
- Martin Kynčl (ORCID: https://orcid.org/0000-0001-6210-6351)
- Andrea Burgetová (ORCID: https://orcid.org/0000-0002-9975-2338)
- Lukáš Lambert (ORCID: https://orcid.org/0000-0003-2299-4707)
- Vanesa Junquero
- Laura Oleaga (ORCID: https://orcid.org/0000-0001-9702-0451)
- Cristina Merino
- Jakub Pristoupil
- Ozbek Suha Sureyya
Institutions
- Charles University (CZ)
- University Hospital in Motol (CZ)
- Hospital Clínic de Barcelona (ES)
- General University Hospital in Prague (CZ)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2025-03-22
- DOI
- https://doi.org/10.1186/s13244-025-01941-7
- Citations
- 4
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 2.62
Funders
- Univerzita Karlova v Praze
- Ministerstvo Zdravotnictví Ceské Republiky