Can artificial intelligence pass the test? Evaluating chatbot scores on pediatric gastroenterology board‐style questions
OpenAI ChatGPT-4o and Microsoft Copilot consistently passed the PREP® GI Self-Assessments from 2022 to 2024, showing potential for good performance on the pediatric GI boards. OpenAI ChatGPT-3.5 had limitations, passing only the 2023 and 2024 assessments. Overall, advanced AI chatbots show potential to pass the Pediatric GI board exam.
Authors
- Annette G. Roberts (ORCID: https://orcid.org/0000-0003-2475-0167)
- S. V. Babu (ORCID: https://orcid.org/0000-0002-5171-261X)
- Matthew Engelhard (ORCID: https://orcid.org/0000-0003-4112-9639)
- Rachel G. Greenberg (ORCID: https://orcid.org/0000-0003-4156-8543)
- Reshma Patel
- Arun Ajmera (ORCID: https://orcid.org/0009-0007-2640-8070)
Institutions
- Duke University (US)
- Clinical Research Institute (US)
- Duke University Hospital (US)
Publication Details
- Journal
- JPGN Reports
- Published
- 2025-11-29
- DOI
- https://doi.org/10.1002/jpr3.70121
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Institute of Mental Health