Automated Evaluation of Reflection and Feedback Quality in Workplace-Based Assessments by Using Natural Language Processing: Cross-Sectional Competency-Based Medical Education Study
BERT-based NLP demonstrated moderate-to-high accuracy in evaluating the narrative quality in EPA assessments, especially in the binary classification. While not a replacement for expert review, NLP models offer a valuable tool for monitoring narrative trends and enhancing formative feedback in competency-based medical education.
Authors
- Wei‐Chung Hsu (ORCID: https://orcid.org/0000-0001-8583-8459)
- Chun‐Hsiang Chang (ORCID: https://orcid.org/0000-0002-4344-4766)
- Huynh Pham Tu
- Pa‐Chun Wang (ORCID: https://orcid.org/0000-0002-6288-9218)
- Mingchih Chen (ORCID: https://orcid.org/0000-0002-8278-0033)
- Chun-Hou Liao
- Jeng‐Wen Chen (ORCID: https://orcid.org/0000-0003-3635-4815)
Institutions
- Fu Jen Catholic University (TW)
- China Medical University (TW)
- China Medical University Hospital (TW)
- Cathay General Hospital (TW)
- National Taiwan University Hospital (TW)
- Cardinal Tien College of Healthcare and Management (TW)
Publication Details
- Journal
- JMIR Medical Education
- Published
- 2025-10-22
- DOI
- https://doi.org/10.2196/81718
- Citations
- 1
- Primary Topic
- Innovations in Medical Education
- Type
- article
- Field-Weighted Citation Impact
- 1.88