{
  "abstract": "Background\n\nLarge language models (LLMs) increasingly provide nutrient information, but their accuracy for Chinese foods and their consistency across repeated queries are not well established.Objective\n\nTo compare nutrient estimates from nine general-purpose LLMs with the Chinese Food Composition Table (CFCT) and assess within-model reproducibility.Methods\n\nFor 299 commonly consumed Chinese foods, each model estimated energy and 14 nutrients per 100 g 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-Altman limits of agreement. Repeated-run ICCs and coefficients of variation assessed reproducibility.Results\n\nAgreement 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.Conclusion\n\nGeneral-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.",
  "abstract_shown": true,
  "affiliations": [
    "Gansu Provincial Maternal and Child Health Care Hospital (Gansu Provincial Central Hospital), Lanzhou, Gansu Province, China.",
    "Gansu University of Chinese Medicine, Lanzhou, Gansu Province, China."
  ],
  "article_type": "research article",
  "arxiv": null,
  "author_total": 5,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Yongwen Cao"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Zhendong Liu"
    },
    {
      "affs": [
        0
      ],
      "name": "Ning Wang"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Min Chen"
    },
    {
      "affs": [
        0,
        1
      ],
      "name": "Hongyan Wang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/b33j1gnrka24p.bib",
  "cited_by": 0,
  "doi": "10.3389/fnut.2026.1952757",
  "fulltext_url": "https://europepmc.org/articles/PMC13677351",
  "id": "b33j1gnrka24p",
  "issns": [
    "2296-861X"
  ],
  "landing_url": "https://europepmc.org/article/MED/42898137",
  "language": "eng",
  "licence": "CC-BY",
  "licence_label": "CC BY",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7219851981",
  "pdf_url": "https://europepmc.org/articles/PMC13677351?pdf=render",
  "pmcid": "PMC13677351",
  "pmid": "42898137",
  "published": "2026-10-05",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/b33j1gnrka24p.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:19:37Z",
      "native_id": "MED:42898137",
      "source": "europepmc",
      "url": "https://europepmc.org/article/MED/42898137"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "openalex:2718|Artificial Intelligence in Healthcare and Education",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Text-based nutrient estimation by large language models: a comparative evaluation against the Chinese Food Composition Table.",
  "title_text": "Text-based nutrient estimation by large language models: a comparative evaluation against the Chinese Food Composition Table.",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:19:37Z",
  "url": "https://research.draconitic.com/paper/b33j1gnrka24p",
  "venue": "Frontiers in nutrition",
  "versions": []
}