Assessment of the Reliability and Clinical Applicability of ChatGPT's Responses to Patients' Common Queries About Rosacea.

Sihan Yan, Dan Du, Xu Liu, Yingying Dai, Min-Kyu Kim, Xinyu Zhou, Lian Wang, Lu Zhang, Xian Jiang
Author Information
  1. Sihan Yan: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China. ORCID
  2. Dan Du: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China. ORCID
  3. Xu Liu: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China. ORCID
  4. Yingying Dai: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China.
  5. Min-Kyu Kim: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China. ORCID
  6. Xinyu Zhou: Department of Dermatology, Nanbu County People's Hospital, Nanbu County, Nanchong, Sichuan, People's Republic of China.
  7. Lian Wang: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China.
  8. Lu Zhang: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China.
  9. Xian Jiang: Department of Dermatology, West China Hospital, Sichuan University, Chengdu, People's Republic of China. ORCID

Abstract

Objective: Artificial intelligence chatbot, particularly ChatGPT (Chat Generative Pre-trained Transformer), is capable of analyzing human input and generating human-like responses, which shows its potential application in healthcare. People with rosacea often have questions about alleviating symptoms and daily skin-care, which is suitable for ChatGPT to response. This study aims to assess the reliability and clinical applicability of ChatGPT 3.5 in responding to patients' common queries about rosacea and to evaluate the extent of ChatGPT's coverage in dermatology resources.
Methods: Based on a qualitative analysis of the literature on the queries from rosacea patients, we have extracted 20 questions of patients' greatest concerns, covering four main categories: treatment, triggers and diet, skincare, and special manifestations of rosacea. Each question was inputted into ChatGPT separately for three rounds of question-and-answer conversations. The generated answers will be evaluated by three experienced dermatologists with postgraduate degrees and over five years of clinical experience in dermatology, to assess their reliability and applicability for clinical practice.
Results: The analysis results indicate that the reviewers unanimously agreed that ChatGPT achieved a high reliability of 92.22% to 97.78% in responding to patients' common queries about rosacea. Additionally, almost all answers were applicable for supporting rosacea patient education, with a clinical applicability ranging from 98.61% to 100.00%. The consistency of the expert ratings was excellent (all significance levels were less than 0.05), with a consistency coefficient of 0.404 for content reliability and 0.456 for clinical practicality, indicating significant consistency in the results and a high level of agreement among the expert ratings.
Conclusion: ChatGPT 3.5 exhibits excellent reliability and clinical applicability in responding to patients' common queries about rosacea. This artificial intelligence tool is applicable for supporting rosacea patient education.

Keywords

References

  1. JMIR Dermatol. 2023 Nov 14;6:e50409 [PMID: 37962920]
  2. Radiology. 2023 May;307(4):e230424 [PMID: 37014239]
  3. Lancet Digit Health. 2023 Mar;5(3):e102 [PMID: 36754723]
  4. Br J Dermatol. 2018 Aug;179(2):282-289 [PMID: 29478264]
  5. JAMA Oncol. 2023 Oct 1;9(10):1437-1440 [PMID: 37615960]
  6. Dermatol Clin. 2018 Apr;36(2):171-174 [PMID: 29499801]
  7. Eur Urol. 2024 Jan;85(1):13-16 [PMID: 37567827]
  8. J Am Acad Dermatol. 2023 Sep;89(3):602-604 [PMID: 37207953]
  9. JAMA. 2023 Mar 14;329(10):842-844 [PMID: 36735264]
  10. Healthcare (Basel). 2023 Aug 29;11(17): [PMID: 37685452]
  11. J Eur Acad Dermatol Venereol. 2010 May;24(5):565-71 [PMID: 19874433]
  12. J Am Acad Dermatol. 2015 May;72(5):761-70; quiz 771-2 [PMID: 25890456]
  13. Nature. 2015 Feb 26;518(7540):529-33 [PMID: 25719670]
  14. J Am Coll Radiol. 2023 Sep 1;: [PMID: 37659450]
  15. JMIR Form Res. 2022 Dec 2;6(12):e39443 [PMID: 36327383]
  16. J Dermatolog Treat. 2016;27(2):99-102 [PMID: 26815357]
  17. J Allergy Clin Immunol Pract. 2023 Sep;11(9):2697-2700 [PMID: 37301435]
  18. Front Artif Intell. 2023 Apr 05;6:1166014 [PMID: 37091303]
  19. Skin Res Technol. 2023 Nov;29(11):e13417 [PMID: 38009033]
  20. Arch Dermatol Res. 2023 Dec;315(10):2979-2981 [PMID: 37668714]

Word Cloud

Created with Highcharts 10.0.0rosaceaChatGPTclinicalreliabilityapplicabilitypatients'queriesintelligencerespondingcommonpatienteducationconsistency0questionsassess35ChatGPT'sdermatologyanalysisthreeanswersresultshighapplicablesupportingexpertratingsexcellentartificialObjective:ArtificialchatbotparticularlyChatGenerativePre-trainedTransformercapableanalyzinghumaninputgeneratinghuman-likeresponsesshowspotentialapplicationhealthcarePeopleoftenalleviatingsymptomsdailyskin-caresuitableresponsestudyaimsevaluateextentcoverageresourcesMethods:Basedqualitativeliteraturepatientsextracted20greatestconcernscoveringfourmaincategories:treatmenttriggersdietskincarespecialmanifestationsquestioninputtedseparatelyroundsquestion-and-answerconversationsgeneratedwillevaluatedexperienceddermatologistspostgraduatedegreesfiveyearsexperiencepracticeResults:indicatereviewersunanimouslyagreedachieved9222%9778%Additionallyalmostranging9861%10000%significancelevelsless05coefficient404content456practicalityindicatingsignificantlevelagreementamongConclusion:exhibitstoolAssessmentReliabilityClinicalApplicabilityResponsesPatients'CommonQueriesRosacea

Similar Articles

Cited By