Medical exam question difficulty prediction: An analysis of embedding representations, machine-learning approaches, and input feature impact
These findings offer valuable insights for data-driven measurement practices including Automated Item Calibration, Computerized Adaptive Testing, and Intelligent Tutoring Systems in medical education. Furthermore, this study revealed that the optimal feature set for difficulty prediction is contingent on the item style. Future research should extend this line of inquiry to the difficulty prediction of Multimodal test items. [Box: see text].
Authors
- Hsueh‐Ming Hang (ORCID: https://orcid.org/0000-0001-8965-2619)
- S. H. Feng (ORCID: https://orcid.org/0000-0002-3946-4043)
- Zhehan Jiang (ORCID: https://orcid.org/0000-0002-1376-9439)
- Jiayi Liu (ORCID: https://orcid.org/0000-0003-2432-4627)
- Tianle Zheng (ORCID: https://orcid.org/0000-0001-5553-3742)
Institutions
- King University (US)
- Peking University (CN)
- National Institute for Communicable Disease Control and Prevention (CN)
Publication Details
- Journal
- Medical Teacher
- Published
- 2025-11-21
- DOI
- https://doi.org/10.1080/0142159x.2025.2586619
- Primary Topic
- Intelligent Tutoring Systems and Adaptive Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00