ChatGPT-4o as a diagnostic tool for skin cancer: Diagnostic accuracy in melanoma and non-melanoma detection
ChatGPT-4o showed variable diagnostic accuracy for melanoma and non-melanoma skin cancers. Dermoscopic images reduced performance for certain diagnostic categories. These misclassifications highlight the potential for unnecessary interventions and patient anxiety underscoring that AI-based systems should serve as supportive aids rather than standalone diagnostic tools.
Authors
- Esranur Ünal (ORCID: https://orcid.org/0000-0002-8309-6452)
- Bengü Nisa Akay (ORCID: https://orcid.org/0000-0002-4896-1666)
- Muhammed Burak Yücel (ORCID: https://orcid.org/0000-0003-0130-8229)
- Saadet Nurşah Gedikli (ORCID: https://orcid.org/0009-0007-6494-2194)
Institutions
- Ankara University (TR)
- Ufuk University (TR)
- Kayseri Eğitim ve Araştırma Hastanesi (TR)
- Sağlık Bilimleri Üniversitesi (TR)
Publication Details
- Journal
- Cutaneous and Ocular Toxicology
- Published
- 2025-12-08
- DOI
- https://doi.org/10.1080/15569527.2025.2598573
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 0.00