JOURNAL ARTICLE

Evaluation of ChatGPT's acne advice.

  • Published In: Clinical & Experimental Dermatology, 2024, v. 49, n. 7. P. 746 1 of 3

  • Database: Academic Search Ultimate 2 of 3

  • Authored By: Li, Kaiyang; Hsu, Jeffrey T S; Li, Monica K 3 of 3

Abstract

This study examines the responses given by OpenAI's ChatGPT, an AI chatbot, to questions about acne. Two dermatologists evaluated the responses based on accuracy, completeness, and relevance. The study found that 40% of the responses met satisfactory standards for accuracy, completeness, and relevance. Treatment-related questions had fewer satisfactory responses compared to basic and acne-type questions. The study also assessed the understandability and actionability of the responses using the Patient Education Materials Assessment Tool (PEMAT) and their readability using the Flesch Reading Ease Score (FRES). Overall, the study provides insights into the usefulness and quality of information provided by ChatGPT for acne patients. However, it suggests that while AI models like ChatGPT can be helpful as a preliminary resource, they should not replace thorough consultations with a dermatologist. Further research is needed to evaluate the performance of AI models with less common skin conditions and other natural language models. [Extracted from the article]

Additional Information

  • Source:Clinical & Experimental Dermatology. 2024/07, Vol. 49, Issue 7, p746
  • Document Type:Article
  • Subject Area:Complementary and Alternative Medicine
  • Publication Date:2024
  • ISSN:0307-6938
  • DOI:10.1093/ced/llad434
  • Accession Number:178321138
  • Copyright Statement:Copyright of Clinical & Experimental Dermatology is the property of Oxford University Press / USA and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Looking to go deeper into this topic? Look for more articles on EBSCOhost.