ChatGPT-Generated Advice on Sun Protection and Skin Cancer Prevention Compared to American Academy of Dermatology Guidelines: Cross-Sectional Content Analysis.

BACKGROUND: Artificial intelligence tools such as ChatGPT are increasingly used by the public to seek health-related information. However, the accuracy and quality of artificial intelligence-generated dermatological guidance, particularly regarding sun protection and skin cancer prevention, have not been systematically assessed. OBJECTIVE: This study aimed to evaluate the quality of ChatGPT-generated responses to common patient questions on sun protection and skin cancer prevention by benchmarking them against guidelines from the American Academy of Dermatology. METHODS: Nine standardized questions reflecting common public inquiries were submitted to ChatGPT (GPT-4 free tier) in a single session on May 13, 2025. Responses were independently evaluated by 2 board-certified consultant dermatologists (>15 years' experience each) across 4 domains (accuracy, completeness, clarity, and relevance) using an author-developed 5-point ordinal rating scale anchored to American Academy of Dermatology guidelines. Scoring disagreements were resolved through discussion between raters until consensus was reached. Interrater reliability was assessed using the linear weighted Cohen κ and intraclass correlation coefficient. RESULTS: Overall mean scores were 5.0 (SD 0.0) for accuracy (ceiling effect observed), 4.1 (SD 0.6) for completeness, 5.0 (SD 0.0) for clarity (ceiling effect observed), and 4.9 (SD 0.3) for relevance, yielding an overall mean of 4.75/5.0 (SD 0.49). Interrater reliability was excellent (weighted Cohen κ=0.80; intraclass correlation coefficient=0.85; exact agreement on 33/36, 91.7% of the items). Completeness was the lowest-scoring domain (range 3.0-5.0), primarily reflecting errors of omission rather than commission. CONCLUSIONS: ChatGPT provided largely accurate and guideline-consistent advice on sun protection and skin cancer prevention in this targeted content analysis. Its primary limitation was incomplete coverage of nuanced guideline details. While not a replacement for professional health care, ChatGPT may serve as a valuable adjunct tool for public health education on skin cancer prevention provided that its outputs are subject to ongoing, systematic evaluation.