Evaluation of ChatGPT Performance on Emergency Medicine Board Examination Questions: Observational Study
The findings suggest that while newer versions of ChatGPT exhibit improved performance in emergency medicine board examination preparation, specific enhancement with a comprehensive Anki flashcard deck on the topic does not significantly impact accuracy. The study highlights the potential of ChatGPT-4 as a tool for medical education, capable of providing accurate support across a wide range of topics in emergency medicine in its default form.
Authors
- Andrew Lafree (ORCID: https://orcid.org/0000-0002-4817-1664)
- Sten Kajitani (ORCID: https://orcid.org/0009-0007-5752-6432)
- Anthony James Goodings (ORCID: https://orcid.org/0009-0005-9702-0968)
- Mila Pastrak (ORCID: https://orcid.org/0009-0005-4423-8197)
- Austin Drewek
- Adrian Murphy (ORCID: https://orcid.org/0000-0002-9417-3580)
Institutions
- Johns Hopkins University (US)
- University of San Diego (US)
- University College Cork (IE)
- Cork University Hospital (IE)
- University of California San Diego (US)
Publication Details
- Journal
- JMIR AI
- Published
- 2025-02-12
- DOI
- https://doi.org/10.2196/67696
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31