Enhancing <scp>AI</scp> 's ability to interpret histological images with prompt engineering: An evaluation of <scp>GPT</scp> ‐4o performance
= 0.004). This study demonstrates that GPT-4o's performance in histological image interpretation varies significantly across tissue types and question complexity. Tissue-specific approaches and a focus on structural identification accuracy are essential for effective educational integration, whereas prompt engineering alone yields limited performance gains.
Authors
- Olena Bolgova (ORCID: https://orcid.org/0009-0002-9496-9754)
- Ahmed Yaqinuddin (ORCID: https://orcid.org/0000-0001-7536-910X)
- Aftab Ahmed Shaikh (ORCID: https://orcid.org/0009-0009-4236-5933)
- Volodymyr Mavrych (ORCID: https://orcid.org/0009-0009-1159-4573)
- Einas M. Yousef
Institutions
- Alfaisal University (SA)
Publication Details
- Journal
- Anatomical Sciences Education
- Published
- 2026-04-01
- DOI
- https://doi.org/10.1002/ase.70209
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00