GP or ChatGPT? Ability of large language models (LLMs) to support general practitioners when prescribing antibiotics.

IF 3.9 2区 医学 Q1 INFECTIOUS DISEASES Journal of Antimicrobial Chemotherapy Pub Date : 2025-03-13 DOI:10.1093/jac/dkaf077
Oanh Ngoc Nguyen, Doaa Amin, James Bennett, Øystein Hetlevik, Sara Malik, Andrew Tout, Heike Vornhagen, Akke Vellinga
{"title":"GP or ChatGPT? Ability of large language models (LLMs) to support general practitioners when prescribing antibiotics.","authors":"Oanh Ngoc Nguyen, Doaa Amin, James Bennett, Øystein Hetlevik, Sara Malik, Andrew Tout, Heike Vornhagen, Akke Vellinga","doi":"10.1093/jac/dkaf077","DOIUrl":null,"url":null,"abstract":"<p><strong>Introduction: </strong>Large language models (LLMs) are becoming ubiquitous and widely implemented. LLMs could also be used for diagnosis and treatment. National antibiotic prescribing guidelines are customized and informed by local laboratory data on antimicrobial resistance.</p><p><strong>Methods: </strong>Based on 24 vignettes with information on type of infection, gender, age group and comorbidities, GPs and LLMs were prompted to provide a treatment. Four countries (Ireland, UK, USA and Norway) were included and a GP from each country and six LLMs (ChatGPT, Gemini, Copilot, Mistral AI, Claude and Llama 3.1) were provided with the vignettes, including their location (country). Responses were compared with the country's national prescribing guidelines. In addition, limitations of LLMs such as hallucination, toxicity and data leakage were assessed.</p><p><strong>Results: </strong>GPs' answers to the vignettes showed high accuracy in relation to diagnosis (96%-100%) and yes/no antibiotic prescribing (83%-92%). GPs referenced (100%) and prescribed (58%-92%) according to national guidelines, but dose/duration of treatment was less accurate (50%-75%). Overall, the GPs' accuracy had a mean of 74%. LLMs scored high in relation to diagnosis (92%-100%), antibiotic prescribing (88%-100%) and the choice of antibiotic (59%-100%) but correct referencing often failed (38%-96%), in particular for the Norwegian guidelines (0%-13%). Data leakage was shown to be an issue as personal information was repeated in the models' responses to the vignettes.</p><p><strong>Conclusions: </strong>LLMs may be safe to guide antibiotic prescribing in general practice. However, to interpret vignettes, apply national guidelines and prescribe the right dose and duration, GPs remain best placed.</p>","PeriodicalId":14969,"journal":{"name":"Journal of Antimicrobial Chemotherapy","volume":" ","pages":""},"PeriodicalIF":3.9000,"publicationDate":"2025-03-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Antimicrobial Chemotherapy","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/jac/dkaf077","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"INFECTIOUS DISEASES","Score":null,"Total":0}
引用次数: 0

Abstract

Introduction: Large language models (LLMs) are becoming ubiquitous and widely implemented. LLMs could also be used for diagnosis and treatment. National antibiotic prescribing guidelines are customized and informed by local laboratory data on antimicrobial resistance.

Methods: Based on 24 vignettes with information on type of infection, gender, age group and comorbidities, GPs and LLMs were prompted to provide a treatment. Four countries (Ireland, UK, USA and Norway) were included and a GP from each country and six LLMs (ChatGPT, Gemini, Copilot, Mistral AI, Claude and Llama 3.1) were provided with the vignettes, including their location (country). Responses were compared with the country's national prescribing guidelines. In addition, limitations of LLMs such as hallucination, toxicity and data leakage were assessed.

Results: GPs' answers to the vignettes showed high accuracy in relation to diagnosis (96%-100%) and yes/no antibiotic prescribing (83%-92%). GPs referenced (100%) and prescribed (58%-92%) according to national guidelines, but dose/duration of treatment was less accurate (50%-75%). Overall, the GPs' accuracy had a mean of 74%. LLMs scored high in relation to diagnosis (92%-100%), antibiotic prescribing (88%-100%) and the choice of antibiotic (59%-100%) but correct referencing often failed (38%-96%), in particular for the Norwegian guidelines (0%-13%). Data leakage was shown to be an issue as personal information was repeated in the models' responses to the vignettes.

Conclusions: LLMs may be safe to guide antibiotic prescribing in general practice. However, to interpret vignettes, apply national guidelines and prescribe the right dose and duration, GPs remain best placed.

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
求助全文
约1分钟内获得全文 去求助
来源期刊
CiteScore
9.20
自引率
5.80%
发文量
423
审稿时长
2-4 weeks
期刊介绍: The Journal publishes articles that further knowledge and advance the science and application of antimicrobial chemotherapy with antibiotics and antifungal, antiviral and antiprotozoal agents. The Journal publishes primarily in human medicine, and articles in veterinary medicine likely to have an impact on global health.
期刊最新文献
Applying quality improvement methods to reduce antibiotic use in neonates: a systematic review and meta-analysis. Diagnosis and management of refractory and rare moulds. Clinical aspects and recent advances in fungal diseases impacting human health. Coccidioidomycosis: a growing global concern. Diagnosis and management of invasive fungal infections due to non-Aspergillus moulds.
×
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