Evaluating ChatGPT's Utility in Medicine Guidelines Through Web Search Analysis.

Q2 Social Sciences The Permanente journal Pub Date : 2024-04-26 DOI:10.7812/TPP/23.126
J. Dubin, Sandeep S Bains, Daniel Hameed, Zhongming Chen, Erica Gaertner, James Nace, Michael A. Mont, R. Delanois
{"title":"Evaluating ChatGPT's Utility in Medicine Guidelines Through Web Search Analysis.","authors":"J. Dubin, Sandeep S Bains, Daniel Hameed, Zhongming Chen, Erica Gaertner, James Nace, Michael A. Mont, R. Delanois","doi":"10.7812/TPP/23.126","DOIUrl":null,"url":null,"abstract":"INTRODUCTION\nWith the rise of machine learning applications in health care, shifts in medical fields that rely on precise prognostic models and pattern detection tools are anticipated in the near future. Chat Generative Pretrained Transformer (ChatGPT) is a recent machine learning innovation known for producing text that mimics human conversation. To gauge ChatGPT's capability in addressing patient inquiries, the authors set out to juxtapose it with Google Search, America's predominant search engine. Their comparison focused on: 1) the top questions related to clinical practice guidelines from the American Academy of Family Physicians by category and subject; 2) responses to these prevalent questions; and 3) the top questions that elicited a numerical reply.\n\n\nMETHODS\nUtilizing a freshly installed Google Chrome browser (version 109.0.5414.119), the authors conducted a Google web search (www.google.com) on March 4, 2023, ensuring minimal influence from personalized search algorithms. Search phrases were derived from the clinical guidelines of the American Academy of Family Physicians. The authors prompted ChatGPT with: \"Search Google using the term '(refer to search terms)' and document the top four questions linked to the term.\" The same 25 search terms were employed. The authors cataloged the primary 4 questions and their answers for each term, resulting in 100 questions and answers.\n\n\nRESULTS\nOf the 100 questions, 42% (42 questions) were consistent across all search terms. ChatGPT predominantly sourced from academic (38% vs 15%, p = 0.0002) and government (50% vs 39%, p = 0.12) domains, whereas Google web searches leaned toward commercial sources (32% vs 11%, p = 0.0002). Thirty-nine percent (39 questions) of the questions yielded divergent answers between the 2 platforms. Notably, 16 of the 39 distinct answers from ChatGPT lacked a numerical reply, instead advising a consultation with a medical professional for health guidance.\n\n\nCONCLUSION\nGoogle Search and ChatGPT present varied questions and answers for both broad and specific queries. Both patients and doctors should exercise prudence when considering ChatGPT as a digital health adviser. It's essential for medical professionals to assist patients in accurately communicating their online discoveries and ensuing inquiries for a comprehensive discussion.","PeriodicalId":23037,"journal":{"name":"The Permanente journal","volume":"3 3","pages":"1-15"},"PeriodicalIF":0.0000,"publicationDate":"2024-04-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"The Permanente journal","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.7812/TPP/23.126","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"Social Sciences","Score":null,"Total":0}
引用次数: 0

Abstract

INTRODUCTION With the rise of machine learning applications in health care, shifts in medical fields that rely on precise prognostic models and pattern detection tools are anticipated in the near future. Chat Generative Pretrained Transformer (ChatGPT) is a recent machine learning innovation known for producing text that mimics human conversation. To gauge ChatGPT's capability in addressing patient inquiries, the authors set out to juxtapose it with Google Search, America's predominant search engine. Their comparison focused on: 1) the top questions related to clinical practice guidelines from the American Academy of Family Physicians by category and subject; 2) responses to these prevalent questions; and 3) the top questions that elicited a numerical reply. METHODS Utilizing a freshly installed Google Chrome browser (version 109.0.5414.119), the authors conducted a Google web search (www.google.com) on March 4, 2023, ensuring minimal influence from personalized search algorithms. Search phrases were derived from the clinical guidelines of the American Academy of Family Physicians. The authors prompted ChatGPT with: "Search Google using the term '(refer to search terms)' and document the top four questions linked to the term." The same 25 search terms were employed. The authors cataloged the primary 4 questions and their answers for each term, resulting in 100 questions and answers. RESULTS Of the 100 questions, 42% (42 questions) were consistent across all search terms. ChatGPT predominantly sourced from academic (38% vs 15%, p = 0.0002) and government (50% vs 39%, p = 0.12) domains, whereas Google web searches leaned toward commercial sources (32% vs 11%, p = 0.0002). Thirty-nine percent (39 questions) of the questions yielded divergent answers between the 2 platforms. Notably, 16 of the 39 distinct answers from ChatGPT lacked a numerical reply, instead advising a consultation with a medical professional for health guidance. CONCLUSION Google Search and ChatGPT present varied questions and answers for both broad and specific queries. Both patients and doctors should exercise prudence when considering ChatGPT as a digital health adviser. It's essential for medical professionals to assist patients in accurately communicating their online discoveries and ensuing inquiries for a comprehensive discussion.
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
通过网络搜索分析评估 ChatGPT 在医学指南中的实用性。
简介随着机器学习在医疗保健领域应用的兴起,预计在不久的将来,依赖精确预后模型和模式检测工具的医疗领域将发生转变。Chat Generative Pretrained Transformer(ChatGPT)是最近的一项机器学习创新,以生成模仿人类对话的文本而闻名。为了衡量 ChatGPT 解决患者咨询的能力,作者将其与谷歌搜索(美国最主要的搜索引擎)进行了对比。他们比较的重点是方法作者使用新安装的谷歌 Chrome 浏览器(版本 109.0.5414.119),在 2023 年 3 月 4 日进行了一次谷歌网络搜索 (www.google.com),确保将个性化搜索算法的影响降至最低。搜索词组来自美国家庭医生学会的临床指南。作者对 ChatGPT 进行了提示:"使用术语'(参考搜索词)'搜索谷歌,并记录与该术语相关的前四个问题"。同样使用了 25 个搜索词。结果 在这 100 个问题中,42%(42 个问题)在所有搜索词中都是一致的。ChatGPT 主要来自学术领域(38% vs 15%,p = 0.0002)和政府领域(50% vs 39%,p = 0.12),而 Google 网页搜索则倾向于商业来源(32% vs 11%,p = 0.0002)。39%的问题(39 个问题)在两个平台上得到了不同的答案。值得注意的是,在来自 ChatGPT 的 39 个不同答案中,有 16 个缺乏数字回答,而是建议咨询医疗专业人士以获得健康指导。在将 ChatGPT 作为数字健康顾问时,患者和医生都应谨慎行事。医疗专业人员必须协助患者准确传达他们的在线发现和随后的询问,以便进行全面讨论。
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
The Permanente journal
The Permanente journal Medicine-Medicine (all)
CiteScore
2.20
自引率
0.00%
发文量
86
期刊最新文献
Survey of Orthopedic Surgeons' Perceptions of Adopting an Initiative With Cemented Hip Hemiarthroplasties for Fractures. Impact of the Graphic Memoir My Degeneration: A Journey Through Parkinson's on Patients With Parkinson's Disease: A Mixed Methods Study. A Comparison of In-Person and Telemedicine Triage in Otolaryngology. Delusional Parasitosis in a Patient With a History of COVID-19 and Substance Use Disorder. Erratum to Vitamin D Deficiency-Associated Neuropathic Pain Examined in a Chronic Pain Management Program.
×
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