从证据到建议与大型语言模型:可行性研究。

IF 3.5 2区 医学 Q1 MEDICINE, GENERAL & INTERNAL
Weilong Zhao, Danni Xia, Ziying Ye, Honghao Lai, Mingyao Sun, Jiajie Huang, Jiayi Liu, Jianing Liu, Long Ge
{"title":"从证据到建议与大型语言模型:可行性研究。","authors":"Weilong Zhao, Danni Xia, Ziying Ye, Honghao Lai, Mingyao Sun, Jiajie Huang, Jiayi Liu, Jianing Liu, Long Ge","doi":"10.1111/jebm.70067","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Formulating evidene-based recommendations for practice guidelines is a complex process that requires substantial expertise. Artificial intelligence (AI) is promising in accelerating the guideline development process. This study evaluates the feasibility of leveraging five large language models (LLMs)-ChatGPT-3.5, Claude-3 sonnet, Bard, ChatGLM-4, Kimi chat-to generate recommendations based on structured evidence, assesses their concordance, and explores the potential for AI.</p><p><strong>Methods: </strong>The general and specific prompts were drafted and validated. We searched PubMed to include evidence-based guidelines related to health and lifestyle. We randomly selected one recommendation from every included guideline as the sample and extracted the evidence base supporting the selected recommendations. The prompts and evidence were fed into five LLMs to generate structured recommendations.</p><p><strong>Results: </strong>ChatGPT-3.5 demonstrated the highest proficiency in comprehensively extracting and synthesizing evidence to formulate novel insights. Bard consistently adhered to existing guideline principles, aligning its algorithm with these tenets. Claude generated fewer topical recommendations, focusing instead on evidence analysis and mitigating irrelevant information. ChatGLM-4 exhibited a balanced approach, combining evidence extraction with adherence to guideline principles. Kimi showed potential in generating concise and targeted recommendations. Among the six generated recommendations, average consistency ranged from 50% to 91.7%.</p><p><strong>Conclusion: </strong>The findings of this study suggest that LLMs hold immense potential in accelerating the formulation of evidence-based recommendations. LLMs can rapidly and comprehensively extract and synthesize relevant information from structured evidence, generating recommendations that align with the available evidence.</p>","PeriodicalId":16090,"journal":{"name":"Journal of Evidence‐Based Medicine","volume":" ","pages":"e70067"},"PeriodicalIF":3.5000,"publicationDate":"2025-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From Evidence to Recommendations With Large Language Models: A Feasibility Study.\",\"authors\":\"Weilong Zhao, Danni Xia, Ziying Ye, Honghao Lai, Mingyao Sun, Jiajie Huang, Jiayi Liu, Jianing Liu, Long Ge\",\"doi\":\"10.1111/jebm.70067\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><strong>Background: </strong>Formulating evidene-based recommendations for practice guidelines is a complex process that requires substantial expertise. Artificial intelligence (AI) is promising in accelerating the guideline development process. This study evaluates the feasibility of leveraging five large language models (LLMs)-ChatGPT-3.5, Claude-3 sonnet, Bard, ChatGLM-4, Kimi chat-to generate recommendations based on structured evidence, assesses their concordance, and explores the potential for AI.</p><p><strong>Methods: </strong>The general and specific prompts were drafted and validated. We searched PubMed to include evidence-based guidelines related to health and lifestyle. We randomly selected one recommendation from every included guideline as the sample and extracted the evidence base supporting the selected recommendations. The prompts and evidence were fed into five LLMs to generate structured recommendations.</p><p><strong>Results: </strong>ChatGPT-3.5 demonstrated the highest proficiency in comprehensively extracting and synthesizing evidence to formulate novel insights. Bard consistently adhered to existing guideline principles, aligning its algorithm with these tenets. Claude generated fewer topical recommendations, focusing instead on evidence analysis and mitigating irrelevant information. ChatGLM-4 exhibited a balanced approach, combining evidence extraction with adherence to guideline principles. Kimi showed potential in generating concise and targeted recommendations. Among the six generated recommendations, average consistency ranged from 50% to 91.7%.</p><p><strong>Conclusion: </strong>The findings of this study suggest that LLMs hold immense potential in accelerating the formulation of evidence-based recommendations. LLMs can rapidly and comprehensively extract and synthesize relevant information from structured evidence, generating recommendations that align with the available evidence.</p>\",\"PeriodicalId\":16090,\"journal\":{\"name\":\"Journal of Evidence‐Based Medicine\",\"volume\":\" \",\"pages\":\"e70067\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2025-09-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Evidence‐Based Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1111/jebm.70067\",\"RegionNum\":2,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"MEDICINE, GENERAL & INTERNAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Evidence‐Based Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1111/jebm.70067","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

摘要

背景:为实践指南制定基于证据的建议是一个复杂的过程,需要大量的专业知识。人工智能(AI)有望加快指南的制定过程。本研究评估了利用五种大型语言模型(llm)——chatggt -3.5、Claude-3十四行诗、Bard、ChatGLM-4、Kimi聊天——基于结构化证据生成推荐的可行性,评估了它们的一致性,并探索了人工智能的潜力。方法:编制通用提示和特定提示并进行验证。我们在PubMed上搜索了与健康和生活方式相关的循证指南。我们从每个纳入的指南中随机选择一个建议作为样本,并提取支持所选建议的证据基础。这些提示和证据被输入5个法学硕士,以生成结构化的建议。结果:ChatGPT-3.5在综合提取和合成证据以形成新见解方面表现出最高的熟练程度。巴德始终坚持现有的指导原则,使其算法与这些原则保持一致。克劳德提出的专题建议较少,而是侧重于证据分析和减轻不相关的信息。ChatGLM-4展示了一种平衡的方法,将证据提取与遵守指导原则相结合。Kimi展示了在生成简洁而有针对性的推荐方面的潜力。在生成的六项建议中,平均一致性从50%到91.7%不等。结论:本研究的结果表明,法学硕士在加速循证建议的制定方面具有巨大的潜力。法学硕士可以快速、全面地从结构化证据中提取和综合相关信息,生成与现有证据一致的建议。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
From Evidence to Recommendations With Large Language Models: A Feasibility Study.

Background: Formulating evidene-based recommendations for practice guidelines is a complex process that requires substantial expertise. Artificial intelligence (AI) is promising in accelerating the guideline development process. This study evaluates the feasibility of leveraging five large language models (LLMs)-ChatGPT-3.5, Claude-3 sonnet, Bard, ChatGLM-4, Kimi chat-to generate recommendations based on structured evidence, assesses their concordance, and explores the potential for AI.

Methods: The general and specific prompts were drafted and validated. We searched PubMed to include evidence-based guidelines related to health and lifestyle. We randomly selected one recommendation from every included guideline as the sample and extracted the evidence base supporting the selected recommendations. The prompts and evidence were fed into five LLMs to generate structured recommendations.

Results: ChatGPT-3.5 demonstrated the highest proficiency in comprehensively extracting and synthesizing evidence to formulate novel insights. Bard consistently adhered to existing guideline principles, aligning its algorithm with these tenets. Claude generated fewer topical recommendations, focusing instead on evidence analysis and mitigating irrelevant information. ChatGLM-4 exhibited a balanced approach, combining evidence extraction with adherence to guideline principles. Kimi showed potential in generating concise and targeted recommendations. Among the six generated recommendations, average consistency ranged from 50% to 91.7%.

Conclusion: The findings of this study suggest that LLMs hold immense potential in accelerating the formulation of evidence-based recommendations. LLMs can rapidly and comprehensively extract and synthesize relevant information from structured evidence, generating recommendations that align with the available evidence.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Journal of Evidence‐Based Medicine
Journal of Evidence‐Based Medicine MEDICINE, GENERAL & INTERNAL-
CiteScore
11.20
自引率
1.40%
发文量
42
期刊介绍: The Journal of Evidence-Based Medicine (EMB) is an esteemed international healthcare and medical decision-making journal, dedicated to publishing groundbreaking research outcomes in evidence-based decision-making, research, practice, and education. Serving as the official English-language journal of the Cochrane China Centre and West China Hospital of Sichuan University, we eagerly welcome editorials, commentaries, and systematic reviews encompassing various topics such as clinical trials, policy, drug and patient safety, education, and knowledge translation.
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信