{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:52:42Z","timestamp":1791175962611,"version":"4.1.0"},"reference-count":23,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T00:00:00Z","timestamp":1791158400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Nutr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large language models (LLMs) increasingly provide nutrient information, but their accuracy for Chinese foods and their consistency across repeated queries are not well established.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To compare nutrient estimates from nine general-purpose LLMs with the Chinese Food Composition Table (CFCT) and assess within-model reproducibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>For 299 commonly consumed Chinese foods, each model estimated energy and 14 nutrients per 100\u202fg in three independent runs (8,073 food-level outputs). Model means were compared with CFCT values using absolute-agreement intraclass correlation coefficients (ICCs), bias, mean absolute error (MAE), root mean squared error, percentage error, and Bland\u2013Altman limits of agreement. Repeated-run ICCs and coefficients of variation assessed reproducibility.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Agreement was excellent for energy, fat, carbohydrate, sodium, and vitamin C across all nine models, and good to excellent for protein. Performance was less consistent for vitamin A, zinc, iron, and potassium. Repeated-run stability was high for energy and macronutrients but lowest for vitamin A. GLM had the most favorable combined accuracy-stability profile, followed by Minimax and Qwen. Even when aggregate agreement was high, individual food estimates sometimes showed substantial error.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>General-purpose LLMs can approximate energy and macronutrient values for Chinese foods under controlled text-based conditions, but micronutrient estimates remain less dependable. Values intended for clinical or other high-stakes applications should be verified using validated food-composition resources and, where appropriate, qualified nutrition professionals.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnut.2026.1952757","type":"journal-article","created":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:32:52Z","timestamp":1791174772000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text-based nutrient estimation by large language models: a comparative evaluation against the Chinese Food Composition Table"],"prefix":"10.3389","volume":"13","author":[{"given":"Yongwen","family":"Cao","sequence":"first","affiliation":[{"name":"Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital)","place":["Lanzhou, Gansu Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhendong","family":"Liu","sequence":"additional","affiliation":[{"name":"Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital)","place":["Lanzhou, Gansu Province, China"]},{"name":"Gansu University of Chinese Medicine","place":["Lanzhou, Gansu Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ning","family":"Wang","sequence":"additional","affiliation":[{"name":"Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital)","place":["Lanzhou, Gansu Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Chen","sequence":"additional","affiliation":[{"name":"Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital)","place":["Lanzhou, Gansu Province, China"]},{"name":"Gansu University of Chinese Medicine","place":["Lanzhou, Gansu Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital)","place":["Lanzhou, Gansu Province, China"]},{"name":"Gansu University of Chinese Medicine","place":["Lanzhou, Gansu Province, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,5]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/nu11010055","article-title":"Evaluation of new technology-based tools for dietary intake assessment-an ILSI Europe dietary intake and exposure task force evaluation","volume":"11","author":"Eldridge","year":"2018","journal-title":"Nutrients"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/nu14193919","article-title":"Burden of nutritional deficiencies in China: findings from the global burden of disease study 2019","volume":"14","author":"Han","year":"2022","journal-title":"Nutrients"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3390\/nu9040397","article-title":"Do Chinese children get enough micronutrients?","volume":"9","author":"Wang","year":"2017","journal-title":"Nutrients"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"e93944","DOI":"10.2196\/93944","article-title":"Consumer and patient health information seeking with generative AI tools: scoping review of facilitators and barriers","volume":"28","author":"Alon","year":"2026","journal-title":"J Med Internet Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/nu18122017","article-title":"Prompt engineering and model selection for LLM-based nutritional estimation from food images: a multi-dataset investigation","volume":"18","author":"Nakagawa","year":"2026","journal-title":"Nutrients"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/nu17040607","article-title":"An evaluation of ChatGPT for nutrient content estimation from meal photographs","volume":"17","author":"O'Hara","year":"2025","journal-title":"Nutrients"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/nu17223613","article-title":"Image-based dietary energy and macronutrients estimation with ChatGPT-5: cross-source evaluation across escalating context scenarios","volume":"17","author":"Rodr\u00edguez-Jim\u00e9nez","year":"2025","journal-title":"Nutrients"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"7577","DOI":"10.1109\/JBHI.2024.3417280","article-title":"Dietary assessment with multimodal ChatGPT: a systematic analysis","volume":"28","author":"Lo","year":"2024","journal-title":"IEEE J Biomed Health Inform"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"107556","DOI":"10.1016\/j.cdnut.2025.107556","article-title":"Performance evaluation of 3 large language models for nutritional content estimation from food images","volume":"9","author":"Fridolfsson","year":"2025","journal-title":"Current Developments Nutrition"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"2273497","DOI":"10.1080\/07853890.2023.2273497","article-title":"AI-based digital image dietary assessment methods compared to humans and ground truth: a systematic review","volume":"55","author":"Shonkoff","year":"2023","journal-title":"Ann Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"112325","DOI":"10.1016\/j.nut.2023.112325","article-title":"AI dietician: unveiling the accuracy of ChatGPT's nutritional estimations","volume":"119","author":"Haman","year":"2024","journal-title":"Nutrition"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.3390\/clinpract13050104","article-title":"AI-powered renal diet support: performance of ChatGPT, bard AI, and Bing chat","volume":"13","author":"Qarajeh","year":"2023","journal-title":"Clinics Practice"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"101712","DOI":"10.1016\/j.tjnut.2026.101712","article-title":"Evaluation of energy and nutrient estimates from large language models using text-based queries","volume":"156","author":"Lawabni","year":"2026","journal-title":"J Nutr"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/nu17193044","article-title":"Comparison of accuracy in the evaluation of nutritional labels on commercial ready-to-eat meal boxes between professional nutritionists and chatbots","volume":"17","author":"Hsuan","year":"2025","journal-title":"Nutrients"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"110437","DOI":"10.1016\/j.foodres.2021.110437","article-title":"Image-based nutrient estimation for Chinese dishes using deep learning","volume":"147","author":"Ma","year":"2021","journal-title":"Food Research International"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"130994","DOI":"10.1016\/j.foodchem.2021.130994","article-title":"Application of deep learning for image-based Chinese market food nutrients estimation","volume":"373","author":"Ma","year":"2022","journal-title":"Food Chem"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"137525","DOI":"10.1016\/j.foodchem.2023.137525","article-title":"DeepTrayMeal: automatic dietary assessment for Chinese tray meals based on deep learning","volume":"434","author":"Shi","year":"2024","journal-title":"Food Chem"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1038\/s43856-025-01159-0","article-title":"DietAI24 as a framework for comprehensive nutrition estimation using multimodal large language models","volume":"5","author":"Yan","year":"2025","journal-title":"Commun Med"},{"key":"ref19","volume-title":"China Food Composition Tables: Standard Edition","author":"Yang","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"101351","DOI":"10.1016\/j.crfs.2026.101351","article-title":"Large language models in food and nutrition science: opportunities, challenges, and the case of FoodyLLM","volume":"12","author":"Gjorgjevikj","year":"2026","journal-title":"Current Research Food Science"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting Intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"5627","DOI":"10.1111\/dom.70747","article-title":"Accuracy of ChatGPT, Gemini, Claude and DeepSeek in carbohydrate counting","volume":"28","author":"Zagaroli","year":"2026","journal-title":"Diabetes Obes Metab"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"101127","DOI":"10.1016\/j.ajcnut.2025.101127","article-title":"Language models in nutrition and dietetics: a scoping review","volume":"123","author":"O'Hara","year":"2026","journal-title":"Am J Clin Nutr"}],"container-title":["Frontiers in Nutrition"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1952757\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T04:33:07Z","timestamp":1791174787000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnut.2026.1952757\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,5]]},"references-count":23,"alternative-id":["10.3389\/fnut.2026.1952757"],"URL":"https:\/\/doi.org\/10.3389\/fnut.2026.1952757","relation":{},"ISSN":["2296-861X"],"issn-type":[{"value":"2296-861X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,5]]},"article-number":"1952757"}}