Framing bias in a large language model: Prompt framing influences ChatGPT's accuracy in melanoma classification. A diagnostic accuracy study - 18/06/26
Doi : 10.1016/j.jaad.2026.03.056
Daniele Omar Traini, MD a, b, ⁎ 
, Gerardo Palmisano, MD a, b, Alessandro Di Stefani, MD a, b, Ketty Peris, MD, PhD a, b
, Gerardo Palmisano, MD a, b, Alessandro Di Stefani, MD a, b, Ketty Peris, MD, PhD a, b a UOC di Dermatologia, Dipartimento di Scienze Mediche e Chirurgiche Addominali ed Endrocrino Metaboliche, Fondazione Policlinico Universitario A. Gemelli - IRCCS, Rome, Italy
b Department of Dermatology, Università Cattolica del Sacro Cuore, Rome, Italy
∗ Correspondence to: Daniele Omar Traini, MD, UOC di Dermatologia, Dipartimento di Scienze Mediche e Chirurgiche, Fondazione Policlinico Universitario A. Gemelli - IRCCS, Largo A. Gemelli 8, 00168 Rome, Italy UOC di Dermatologia Dipartimento di Scienze Mediche e Chirurgiche Fondazione Policlinico Universitario A. Gemelli - IRCCS Largo A. Gemelli 8 Rome 00168 Italy
Key words : artificial intelligence, dermoscopy, framing bias, imaging, large language models, melanoma
| Funding sources: None. |
|
| Patient consent: Written informed consent was obtained from the individual(s) for the publication of any identifiable images or data included in this article. All patient data were anonymized and handled with strict confidentiality to ensure privacy and compliance with ethical standards. |
|
| IRB approval status: This study was conducted in accordance with the ethical standards of the institutional research committee and the 1964 Helsinki declaration and its later amendments or comparable ethical standards. |
|
| Data availability statement: The data that support the findings of this study are available on request from the corresponding author. |
© 2026
The Author(s). Publié par Elsevier Masson SAS. Tous droits réservés.
Vol 95 - N° 1
P. 277-279 - juillet 2026 Retour au numéro
Article précédent
- Relative survival analysis of dermatofibrosarcoma protuberans, Kaposi sarcoma, and pleomorphic sarcoma across intersectional demographics: A Surveillance, Epidemiology, and End Results (SEER) study
- Benjamin D. Hu, Andrew Zhu, Raphaella Lambert, Brandon R. Block, Grace Rabinowitz, Hannah Verma, Jón Gunnlaugur Jónasson, Bardur Sigurgeirsson, Shane Meehan, Jonathan Ungar, Jesse M. Lewin, Nicholas Gulati, Jonas A. Adalsteinsson
- Enhancing dermatology workflow through a replicable epic-based module: Impact on documentation and after-hours electronic medical record use
- Simona A. Alomary, Nicole J. Baker, Susan C. Taylor, Nicholas K. Mollanazar
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?