Accepted for/Published in: JMIR Dermatology
Date Submitted: Jun 29, 2023
Date Accepted: Oct 30, 2023
Assessing the Accuracy and Comprehensiveness of ChatGPT in Offering Clinical Guidance for Atopic Dermatitis and Acne Vulgaris
ABSTRACT
ChatGPT is a popular artificial intelligence model designed to engage in natural language conversations. It has been trained with a substantial amount of information on the public domain, including textbooks, articles, and websites, as well as conversations between humans. One of the key features of ChatGPT is its ability to generate human-like responses. ChatGPT offers the potential to expand information accessibility, yet despite being trained on vast amounts of data and demonstrating medical competence, literature assessing its utility in offering dermatologic guidance is scant. This descriptive study characterizes the accuracy and comprehensiveness of ChatGPT in responding to potential patient questions for acne vulgaris and atopic dermatitis using independent board-certified dermatologist reviewers and a grading scheme previously referenced in the literature. The findings support that ChatGPT is frequently accurate in providing guidance for these conditions (66–88%), yet less often fully comprehensive (34–53%), often providing logical answers that are at times verbose. These findings provide initial characterization of ChatGPT in the dermatologic setting and should encourage further studies across additional skin conditions moving forward.
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.