Assessing the Accuracy and Comprehensiveness of ChatGPT in Offering Clinical Guidance for Atopic Dermatitis and Acne Vulgaris (Preprint)
Preprint
- 29 June 2023
- preprint
- Published by JMIR Publications Inc. in JMIR Preprints
Abstract
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). 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.Keywords
All Related Versions
- Published version: JMIR Dermatology, 6, e50409.
This publication has 7 references indexed in Scilit:
- Assessing the performance of ChatGPT in answering questions regarding cirrhosis and hepatocellular carcinomaClinical and Molecular Hepatology, 2023
- Appropriateness of Cardiovascular Disease Prevention Recommendations Obtained From a Popular Online Chat-Based Artificial Intelligence ModelJAMA, 2023
- Consulting ChatGPT: Ethical dilemmas in language model artificial intelligenceJournal of the American Academy of Dermatology, 2023
- Guidelines of care for the management of acne vulgarisJournal of the American Academy of Dermatology, 2016
- Guidelines of care for the management of atopic dermatitisJournal of the American Academy of Dermatology, 2014
- The Sagnac effect: correct and incorrect explanationsPhysics-Uspekhi, 2000
- What is atopic dermatitis and how should it be defined in epidemiological studies?2000