ChatGPT-4 reliability when applied to the regional anesthesia technique sonoanatomy
ChatGPT-4 demonstrated high accuracy in identifying anatomical structures and predicting block success on ultrasound images. While performance in classifying certain block types was lower, these findings support the potential of large language models as decision-support tools in ultrasound-guided regional anesthesia.
Authors
- Engin İhsan Turan (ORCID: https://orcid.org/0000-0001-7447-5074)
- Zehra Polat Turan (ORCID: https://orcid.org/0009-0009-8105-8944)
- Abdurrahman Engin Baydemir (ORCID: https://orcid.org/0000-0001-9332-1417)
- Gizem C Eker
- Ayça S Şahin
Institutions
- Istanbul Metropolitan Municipality (TR)
- Sağlık Bilimleri Üniversitesi (TR)
- Şişli Etfal Eğitim ve Araştırma Hastanesi (TR)
- İstanbul Kanuni Sultan Süleyman Eğitim ve Araştırma Hastanesi (TR)
Publication Details
- Journal
- Minerva Anestesiologica
- Published
- 2026-02-01
- DOI
- https://doi.org/10.23736/s0375-9393.25.19538-2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00