Currently submitted to: JMIR Dermatology
Date Submitted: Feb 20, 2026
Open Peer Review Period: Mar 2, 2026 - Apr 27, 2026
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Alignment of ChatGPT-Generated Advice on Sun Protection and Skin Cancer Prevention With American Academy of Dermatology Guidelines: Cross-Sectional Content Analysis
ABSTRACT
Background:
Nowadays, Artificial Intelligence (AI) tools, such as ChatGPT, are increasingly used to provide health-related information. However, the accuracy of this information in dermatology, particularly regarding sun protection and skin cancer prevention, has not been assessed.
Objective:
This study aimed to evaluate the quality of ChatGPT-generated responses to common questions related to sun protection and skin cancer prevention by comparing them with guidelines from the American Academy of Dermatology (AAD).
Methods:
A set of nine commonly asked questions on sun protection and skin cancer prevention was submitted to ChatGPT. Each response was evaluated across four key domains: accuracy, completeness, clarity, and relevance. Scoring was based on alignment with AAD recommendations and assessed independently.
Results:
ChatGPT responses were accurate, clear, and relevant. Most answers closely matched the AAD’s guidance, although a few responses showed slight omissions concerning specific contextual details.
Conclusions:
While not a replacement for professional healthcare, ChatGPT provides valid and accessible information on skin cancer prevention. With regular and strong evaluation, its role in AI-based dermatological tools may become significant in supporting public health education. Clinical Trial: not applicable
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.