{
  "abstract": "BackgroundEstimating nutrient intake from meal photographs with vision-language models (VLMs) is now practical, but patient photographs often cannot leave the institution. We developed PLANS (Personal-device Local Assessment of Nutrients System), in which a small open VLM runs entirely on a personal device.\n\nMethodsOpen VLMs were compared on two image sets with reference values (NutriImage, 887 Japanese meals; SNAPMe, 1,134 US meals), and the selected model (Qwen3-VL-4B, 4-bit) was run on an iPad Air without network access. Energy (primary outcome), protein, fat, carbohydrate and salt were evaluated by median absolute percentage error (MedAPE) and Spearmans {rho}. The effect of supplying the food weight, including errors in it, was examined.\n\nResultsEnergy estimates on the iPad were identical to those of a desktop-computer run for 84-86% of images (other values, 75-87%). MedAPE on the iPad was 37.0% and 36.5% for energy (26-28% of images within {+/-}20%), 43-65% for the macronutrients and 68-101% for salt ({rho} 0.51-0.85). On the desktop computer, supplying the true weight reduced MedAPE of the 4B model on NutriImage from 37.0% to 32.5% for energy and from 100.0% to 66.8% for salt; energy MedAPE stayed below the base value for declared weights of 0.5-1.25 times the true weight or rounded to 50 g, but rose markedly when the container weight was included.\n\nConclusionsAn offline VLM on a tablet reproduced server-side energy accuracy and is a candidate tool for dietary counselling where photographs cannot leave the institution; given the wide limits of agreement, its usefulness in practice remains to be examined.",
  "abstract_shown": true,
  "affiliations": [
    "Research Institute of Info-Communication Medicine"
  ],
  "article_type": "PUBLISHAHEADOFPRINT",
  "arxiv": null,
  "author_total": 2,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "S. Nakagawa"
    },
    {
      "name": "A. Yamamoto"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/0jac47pv9wq2t.bib",
  "cited_by": 0,
  "doi": "10.64898/2026.10.11.26365273",
  "fulltext_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365273v1.full",
  "id": "0jac47pv9wq2t",
  "issns": [],
  "landing_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365273v1",
  "language": null,
  "licence": "CC-BY-ND",
  "licence_label": "CC BY-ND",
  "licence_source": "article",
  "licence_url": "https://creativecommons.org/licenses/by-nd/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "medrxiv",
      "health informatics"
    ],
    [
      "openalex",
      "2718|Artificial Intelligence in Healthcare and Education"
    ]
  ],
  "openalex": "W7221611404",
  "pdf_url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365273v1.full.pdf",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-11",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/0jac47pv9wq2t.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:20:45Z",
      "native_id": "10.64898/2026.10.11.26365273",
      "source": "medrxiv",
      "url": "https://www.medrxiv.org/content/10.64898/2026.10.11.26365273v1"
    }
  ],
  "subjects": [
    {
      "field": "medicine",
      "origin": "medrxiv:health informatics",
      "subfield": "epidemiology-public-health"
    }
  ],
  "title": "Development and Evaluation of an Offline Vision-Language Model System for Estimating Nutrients from Meal Photographs on Personal Devices: The PLANS (Personal-device Local Assessment of Nutrients System) Study",
  "title_text": "Development and Evaluation of an Offline Vision-Language Model System for Estimating Nutrients from Meal Photographs on Personal Devices: The PLANS (Personal-device Local Assessment of Nutrients System) Study",
  "type": "preprint",
  "updated_at": "2026-10-30T12:20:45Z",
  "url": "https://research.draconitic.com/paper/0jac47pv9wq2t",
  "venue": "medRxiv",
  "versions": []
}