Virtual case reasoning and AI-assisted diagnostic instruction: an empirical study based on body interact and large language models
Our findings suggest that ChatGPT-4 and DeepSeek-R1 each offer unique strengths for AI-assisted instruction. ChatGPT-4's accessible language may better support early learners, whereas DeepSeek-R1 may be more aligned with formal clinical reasoning. Selecting models based on specific teaching goals can enhance the effectiveness of AI-driven medical education.
Authors
- Xianxin Li (ORCID: https://orcid.org/0000-0002-5690-0150)
- Yu Seob Shin (ORCID: https://orcid.org/0000-0002-1126-3821)
- Guihua Chen (ORCID: https://orcid.org/0009-0007-0142-3565)
- Lijie Zhang
- Zhao Luo (ORCID: https://orcid.org/0009-0005-7807-6296)
- Chuan Lin (ORCID: https://orcid.org/0009-0005-4204-5375)
Institutions
- Jeonju National University of Education (KR)
- Luohe Medical College (CN)
- Jeonbuk National University Hospital (KR)
- Nanchong Central Hospital (CN)
- Shenzhen Pingle Orthopedic Hospital (CN)
- Anshan Hospital (CN)
- Jeonbuk National University (KR)
Publication Details
- Journal
- BMC Medical Education
- Published
- 2025-10-24
- DOI
- https://doi.org/10.1186/s12909-025-07872-7
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Research Foundation