Enhancing the CAD-RADS™ 2.0 Category Assignment Performance of ChatGPT and DeepSeek Through “Few-shot” Prompting
Few-shot prompting substantially enhances LLMs' accuracy in assigning CAD-RADS™ 2.0 categories, suggesting potential for clinical application and facilitating system adoption.
Authors
- Hasan Emin Kaya (ORCID: https://orcid.org/0000-0002-7411-4102)
Institutions
- Bursa Uludağ Üni̇versi̇tesi̇ (TR)
Publication Details
- Journal
- Journal of Computer Assisted Tomography
- Published
- 2025-09-23
- DOI
- https://doi.org/10.1097/rct.0000000000001802
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00