ChatGPT versus human authors: A comparative study of concept maps for clinical reasoning training with virtual patients
ChatGPT can reliably generate concept maps that match expert-level clinical accuracy. However, limitations in educational clarity and usability underscore the need for expert refinement. With appropriate oversight, large language models (LLMs) such as ChatGPT can support efficient development of learning resources for CR education.
Authors
- Inga Hege (ORCID: https://orcid.org/0000-0003-4335-5162)
- Stanisław Górski (ORCID: https://orcid.org/0000-0002-1740-4082)
- Yavuz Selim Kıyak (ORCID: https://orcid.org/0000-0002-5026-3234)
- Léa Linglart (ORCID: https://orcid.org/0000-0002-0165-9603)
- Dario M. Torre (ORCID: https://orcid.org/0000-0002-4924-4888)
- T. S. Shchudrova (ORCID: https://orcid.org/0000-0003-4186-2013)
- Andrzej A. Kononowicz (ORCID: https://orcid.org/0000-0003-2956-2093)
- Renata Szydlak (ORCID: https://orcid.org/0000-0003-2760-2952)
Institutions
- University of Central Florida (US)
- Jagiellonian University (PL)
- Hôpital Necker-Enfants Malades (FR)
- Bukovinian State Medical University (UA)
- Sorbonne Université (FR)
- Medizinische Hochschule Brandenburg Theodor Fontane (DE)
- Laboratoire Médiations (FR)
- Florida College (US)
- Gazi University (TR)
Publication Details
- Journal
- Medical Teacher
- Published
- 2025-11-12
- DOI
- https://doi.org/10.1080/0142159x.2025.2583403
- Citations
- 1
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.65