Role-based prompting to optimize chatgpt's anatomical assessment

SİVRİ İ., ÖZDEN F. M., GÜL G., KAYGIN E., ÇOLAK T.

SURGICAL AND RADIOLOGIC ANATOMY, cilt.47, sa.1, 2025 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 47 Sayı: 1
  • Basım Tarihi: 2025
  • Doi Numarası: 10.1007/s00276-025-03747-0
  • Dergi Adı: SURGICAL AND RADIOLOGIC ANATOMY
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, CINAHL, MEDLINE
  • Kocaeli Üniversitesi Adresli: Evet

Özet

Recent evaluations of ChatGPT's performance in anatomy education have provided valuable insights into its capabilities and limitations. In response to the article by Singal and Goyal on the use of ChatGPT 3.5 and 4.0 for education on scalenovertebral triangle anatomy, we propose that the "neutral prompt" approach can be further optimized by using role-specific prompts. This approach, already utilized in other medical domains, allows large language models to generate more contextually appropriate and pedagogically useful outputs. We recommend considering the integration of role-specific prompts in future studies assessing AI-based tools in anatomy education, as a means to optimize their reliability and educational value.