Evaluating the effectiveness of ChatGPT4 in the diagnosis and workup of dermatologic conditions.

Q3 Medicine Dermatology online journal Pub Date : 2024-08-15 DOI:10.5070/D330464104
Charlotte Greif, Ndanzia Mpunga, Irene V Koopman, Allison Pye, Chad M Hivnor, Joshua L Owen
{"title":"Evaluating the effectiveness of ChatGPT4 in the diagnosis and workup of dermatologic conditions.","authors":"Charlotte Greif, Ndanzia Mpunga, Irene V Koopman, Allison Pye, Chad M Hivnor, Joshua L Owen","doi":"10.5070/D330464104","DOIUrl":null,"url":null,"abstract":"<p><p>ChatGPT is a publicly available chatbot released by OpenAI. Its usefulness in responding to medical questions has been assessed in several specialties, but there is limited literature in dermatology. This study seeks to understand how well ChatGPT4 can provide accurate diagnoses and appropriate workup suggestions for clinical vignettes describing common dermatologic conditions. Ten vignettes were input into ChatGPT4 representing presentations of common dermatologic conditions, written from the perspective of a physician not board-certified in dermatology. ChatGPT4 was asked to identify the top five most likely diagnoses and its recommended workup for each vignette. Responses were assessed quantitatively by calculating the percentage of correct diagnoses, with accurate diagnoses defined by three board-certified dermatologists, and qualitatively using Likert scales describing the accuracy of diagnoses and appropriateness of workups scored by eleven board-certified dermatologists. Overall, 52% of ChatGPT4's diagnoses were accurate and 62% of its recommended workup suggestions were deemed completely correct by board-certified dermatologists. ChatGPT4 was better at recommending an appropriate workup than identifying accurate diagnoses across vignettes. ChatGPT4 was able to accurately diagnose and workup common dermatologic conditions in slightly more than half of cases. ChatGPT4 was better at determining an appropriate workup than an accurate diagnosis.Keywords: artificial intelligence, ChatGPT, dermatology, diagnosis, OpenAI, workup.</p>","PeriodicalId":11040,"journal":{"name":"Dermatology online journal","volume":"30 4","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-08-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Dermatology online journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5070/D330464104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Medicine","Score":null,"Total":0}
引用次数: 0

Abstract

ChatGPT is a publicly available chatbot released by OpenAI. Its usefulness in responding to medical questions has been assessed in several specialties, but there is limited literature in dermatology. This study seeks to understand how well ChatGPT4 can provide accurate diagnoses and appropriate workup suggestions for clinical vignettes describing common dermatologic conditions. Ten vignettes were input into ChatGPT4 representing presentations of common dermatologic conditions, written from the perspective of a physician not board-certified in dermatology. ChatGPT4 was asked to identify the top five most likely diagnoses and its recommended workup for each vignette. Responses were assessed quantitatively by calculating the percentage of correct diagnoses, with accurate diagnoses defined by three board-certified dermatologists, and qualitatively using Likert scales describing the accuracy of diagnoses and appropriateness of workups scored by eleven board-certified dermatologists. Overall, 52% of ChatGPT4's diagnoses were accurate and 62% of its recommended workup suggestions were deemed completely correct by board-certified dermatologists. ChatGPT4 was better at recommending an appropriate workup than identifying accurate diagnoses across vignettes. ChatGPT4 was able to accurately diagnose and workup common dermatologic conditions in slightly more than half of cases. ChatGPT4 was better at determining an appropriate workup than an accurate diagnosis.Keywords: artificial intelligence, ChatGPT, dermatology, diagnosis, OpenAI, workup.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
评价ChatGPT4在皮肤病诊断和检查中的有效性。
ChatGPT是OpenAI发布的一个公开可用的聊天机器人。它在回答医学问题方面的有用性已经在几个专业进行了评估,但在皮肤病学方面的文献有限。本研究旨在了解ChatGPT4如何为描述常见皮肤病的临床症状提供准确的诊断和适当的检查建议。ChatGPT4输入10个小插曲,代表常见皮肤疾病的表现,从非皮肤病委员会认证的医生的角度编写。ChatGPT4被要求确定前五种最可能的诊断及其对每个小插曲的推荐检查。通过计算正确诊断的百分比来定量评估反应,准确诊断由三名委员会认证的皮肤科医生定义,定性使用李克特量表描述诊断的准确性和11名委员会认证的皮肤科医生评分的检查的适当性。总体而言,52%的ChatGPT4诊断是准确的,62%的推荐检查建议被委员会认证的皮肤科医生认为是完全正确的。ChatGPT4在推荐适当的检查方面优于在小插曲中识别准确的诊断。ChatGPT4能够在略超过一半的病例中准确诊断和检查常见的皮肤病。ChatGPT4在确定适当的检查方面优于准确的诊断。关键词:人工智能,ChatGPT,皮肤科,诊断,OpenAI,体检
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Dermatology online journal
Dermatology online journal Medicine-Dermatology
CiteScore
1.70
自引率
0.00%
发文量
200
审稿时长
6 weeks
期刊介绍: An open-access, refereed publication intended to meet reference and education needs of the international dermatology community since 1995. Dermatology Online Journal is supported by the Department of Dermatology UC Davis, and by the Northern California Veterans Administration.
期刊最新文献
Implementation of the atopic dermatitis yardstick via the electronic medical record: a pilot study to improve clinical documentation and patient education. Lactation anaphylaxis: report of a rare case with recurrent postpartum anaphylaxis. Light-based therapies in the treatment of alopecia. Personalized melanoma grading system: a presentation of a patient with four melanomas detected over two decades with evolving whole-body imaging and artificial intelligence systems. Phacomatosis spilorosea and phacomatosis melanorosea: further phenotype expansion.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1