• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

人工智能工具 ChatGPT 和 Bard 能否为不同的饮食模式生成能量充足、宏量和微量营养素充足的膳食计划?

Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?

机构信息

Max Rubner-Institut, Department of Physiology and Biochemistry of Nutrition, Karlsruhe, Germany.

Department of Chemistry and Pharmacy, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen, Germany; Department of Food Chemistry and Analytical Chemistry (170a), Institute of Food Chemistry, University of Hohenheim, Stuttgart, Germany.

出版信息

Nutr Res. 2024 Aug;128:105-114. doi: 10.1016/j.nutres.2024.07.002. Epub 2024 Jul 14.

DOI:10.1016/j.nutres.2024.07.002
PMID:39102765
Abstract

Artificial intelligence chatbots based on large language models have recently emerged as an alternative to traditional online searches and are also entering the nutrition space. In this study, we wanted to investigate whether the artificial intelligence chatbots ChatGPT and Bard (now Gemini) can create meal plans that meet the dietary reference intake (DRI) for different dietary patterns. We further hypothesized that nutritional adequacy could be improved by modifying the prompts used. Meal plans were generated by 3 accounts for different dietary patterns (omnivorous, vegetarian, and vegan) using 2 distinct prompts resulting in 108 meal plans total. The nutrient content of the plans was subsequently analyzed and compared to the DRIs. On average, the meal plans contained less energy and carbohydrates but mostly exceeded the DRI for protein. Vitamin D and fluoride fell below the DRI for all plans, whereas only the vegan plans contained insufficient vitamin B. ChatGPT suggested using vitamin B supplements in 5 of 18 instances, whereas Bard never recommended supplements. There were no significant differences between the prompts or the tools. Although the meal plans generated by ChatGPT and Bard met most DRIs, there were some exceptions, particularly for vegan diets. These tools maybe useful for individuals looking for general dietary inspiration, but they should not be relied on to create nutritionally adequate meal plans, especially for individuals with restrictive dietary needs.

摘要

基于大型语言模型的人工智能聊天机器人最近作为传统在线搜索的替代品出现,也开始进入营养领域。在这项研究中,我们想调查人工智能聊天机器人 ChatGPT 和 Bard(现在称为 Gemini)是否可以为不同的饮食模式制定符合膳食参考摄入量(DRI)的膳食计划。我们进一步假设通过修改提示词可以提高营养充足度。使用 2 种不同的提示词,由 3 个账户为不同的饮食模式(杂食、素食和纯素)生成了 108 份膳食计划。随后分析了计划的营养成分,并将其与 DRI 进行比较。平均而言,这些膳食计划的能量和碳水化合物含量较低,但蛋白质含量大多超过 DRI。所有计划的维生素 D 和氟化物都低于 DRI,而只有素食计划的维生素 B 含量不足。ChatGPT 在 18 次中有 5 次建议使用维生素 B 补充剂,而 Bard 从未建议补充剂。提示词和工具之间没有显著差异。尽管 ChatGPT 和 Bard 生成的膳食计划符合大多数 DRI,但也有一些例外,特别是对于素食饮食。这些工具可能对寻求一般饮食灵感的个人有用,但不应依赖它们来制定营养充足的膳食计划,特别是对于有严格饮食需求的个人。

相似文献

1
Can the AI tools ChatGPT and Bard generate energy, macro- and micro-nutrient sufficient meal plans for different dietary patterns?人工智能工具 ChatGPT 和 Bard 能否为不同的饮食模式生成能量充足、宏量和微量营养素充足的膳食计划?
Nutr Res. 2024 Aug;128:105-114. doi: 10.1016/j.nutres.2024.07.002. Epub 2024 Jul 14.
2
Theoretical Food and Nutrient Composition of Whole-Food Plant-Based and Vegan Diets Compared to Current Dietary Recommendations.全食物植物性饮食和纯素饮食与当前饮食建议的理论食物及营养素构成比较。
Nutrients. 2019 Mar 14;11(3):625. doi: 10.3390/nu11030625.
3
An Evaluation of ChatGPT for Nutrient Content Estimation from Meal Photographs.ChatGPT用于根据餐食照片估算营养成分的评估
Nutrients. 2025 Feb 7;17(4):607. doi: 10.3390/nu17040607.
4
Meeting recommended dietary intakes in meal plans with ≥4 servings of grain-based foods daily.每日食用≥4 份谷物类食物的膳食计划符合推荐膳食摄入量。
Public Health Nutr. 2013 May;16(5):803-14. doi: 10.1017/S1368980012004764. Epub 2012 Nov 16.
5
Diet Quality and Caloric Accuracy in AI-Generated Diet Plans: A Comparative Study Across Chatbots.人工智能生成的饮食计划中的饮食质量和热量准确性:跨聊天机器人的比较研究。
Nutrients. 2025 Jan 7;17(2):206. doi: 10.3390/nu17020206.
6
Assessment of readability, reliability, and quality of ChatGPT®, BARD®, Gemini®, Copilot®, Perplexity® responses on palliative care.评估 ChatGPT®、BARD®、 Gemini®、Copilot®、Perplexity® 在姑息治疗方面的可读性、可靠性和质量。
Medicine (Baltimore). 2024 Aug 16;103(33):e39305. doi: 10.1097/MD.0000000000039305.
7
Dr. Google to Dr. ChatGPT: assessing the content and quality of artificial intelligence-generated medical information on appendicitis.谷歌博士对 ChatGPT 博士:评估人工智能生成的关于阑尾炎的医学信息的内容和质量。
Surg Endosc. 2024 May;38(5):2887-2893. doi: 10.1007/s00464-024-10739-5. Epub 2024 Mar 5.
8
The nutrient profile and cost of specialty dietary patterns: a hypothetical case study.特殊饮食模式的营养成分和成本:一个假设性案例研究。
Public Health Nutr. 2023 Dec;26(12):2995-3004. doi: 10.1017/S1368980023002537. Epub 2023 Nov 13.
9
Assessing the Reproducibility of the Structured Abstracts Generated by ChatGPT and Bard Compared to Human-Written Abstracts in the Field of Spine Surgery: Comparative Analysis.评估 ChatGPT 和 Bard 生成的结构化摘要与脊柱外科领域人类撰写的摘要在可重复性方面的比较:对比分析。
J Med Internet Res. 2024 Jun 26;26:e52001. doi: 10.2196/52001.
10
Can artificial intelligence (AI) chatbot tools be used effectively for nutritional management in obesity?人工智能(AI)聊天机器人工具能否有效用于肥胖症的营养管理?
Nutr Health. 2025 Mar 20:2601060251329070. doi: 10.1177/02601060251329070.

引用本文的文献

1
Large language models in clinical nutrition: an overview of its applications, capabilities, limitations, and potential future prospects.临床营养中的大语言模型:其应用、能力、局限性及潜在未来前景概述
Front Nutr. 2025 Aug 7;12:1635682. doi: 10.3389/fnut.2025.1635682. eCollection 2025.
2
ChatGPT-4o for Weight Management: Comparison of Different Diet Models.用于体重管理的ChatGPT-4o:不同饮食模式的比较
Food Sci Nutr. 2025 Jul 16;13(7):e70639. doi: 10.1002/fsn3.70639. eCollection 2025 Jul.
3
Assessment of Recommendations Provided to Athletes Regarding Sleep Education by GPT-4o and Google Gemini: Comparative Evaluation Study.
GPT-4o和谷歌Gemini向运动员提供的关于睡眠教育的建议评估:比较评估研究
JMIR Form Res. 2025 Jul 8;9:e71358. doi: 10.2196/71358.
4
Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients.利用大语言模型改进个性化饮食计划:识别与分解复合食材
Nutrients. 2025 Apr 29;17(9):1492. doi: 10.3390/nu17091492.
5
ChatGPT-4o and 4o1 Preview as Dietary Support Tools in a Real-World Medicated Obesity Program: A Prospective Comparative Analysis.ChatGPT-4o和4o1预览版作为现实世界药物性肥胖项目中的饮食支持工具:一项前瞻性比较分析。
Healthcare (Basel). 2025 Mar 16;13(6):647. doi: 10.3390/healthcare13060647.
6
Diet Quality and Caloric Accuracy in AI-Generated Diet Plans: A Comparative Study Across Chatbots.人工智能生成的饮食计划中的饮食质量和热量准确性:跨聊天机器人的比较研究。
Nutrients. 2025 Jan 7;17(2):206. doi: 10.3390/nu17020206.
7
Comparison of the Accuracy, Completeness, Reproducibility, and Consistency of Different AI Chatbots in Providing Nutritional Advice: An Exploratory Study.不同人工智能聊天机器人提供营养建议的准确性、完整性、可重复性和一致性比较:一项探索性研究。
J Clin Med. 2024 Dec 20;13(24):7810. doi: 10.3390/jcm13247810.
8
Comparison of Answers between ChatGPT and Human Dieticians to Common Nutrition Questions.ChatGPT与人类营养师对常见营养问题的回答比较。
J Nutr Metab. 2023 Nov 7;2023:5548684. doi: 10.1155/2023/5548684. eCollection 2023.