ArticleJMIR dermatology2026
ChatGPT-Generated Advice on Sun Protection and Skin Cancer Prevention Compared to American Academy of Dermatology Guidelines: Cross-Sectional Content Analysis.
Article in JMIR dermatology, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
2 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
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.
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.