EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Performance Evaluation of 3 Large Language Models for Nutritional Content Estimation from Food Images

Jonatan Fridolfsson, Emma Sjöberg, Meri Thiwång, Stefan Pettersson

Current Developments in Nutrition · 2025-10 · 9 (10) · 107556

DOI: 10.1016/j.cdnut.2025.107556 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Current Developments in Nutrition, 2025-10. Verfasst von Jonatan Fridolfsson und 3 weiteren Autor:innen. Beteiligte Einrichtung: Center for Lifestyle Intervention, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Traditional dietary assessment methods face limitations including recall bias, participant burden, and portion size estimation errors. Recent advances in artificial intelligence, particularly multimodal large language models (LLMs), offer potential solutions for automated nutritional analysis from food images.

Objectives

This study aims to evaluate and compare the performance of 3 leading LLMs (ChatGPT-4o, Claude 3.5 Sonnet, and Gemini 1.5 Pro) in estimating food weight, energy content, and macronutrient composition from standardized food photographs.

Methods

We analyzed 52 standardized food photographs including individual food components (n = 16) and complete meals (n = 36) in 3 portion sizes (small, medium, large). Each model received identical prompts to identify food components and estimate nutritional content using visible cutlery and plates as size references. Model estimates were compared against reference values obtained through direct weighing and nutritional database analysis (Dietist NET). Performance metrics included mean absolute percentage error (MAPE), Pearson correlations, and systematic bias analysis using Bland-Altman plots.

Results

ChatGPT and Claude demonstrated similar accuracy with MAPE values of 36.3% and 37.3% for weight estimation, and 35.8% for energy estimation. Gemini showed substantially higher errors across all nutrients (MAPE 64.2%-109.9%). Correlations between model estimates and reference values ranged from 0.65 to 0.81 for ChatGPT and Claude, compared with 0.58-0.73 for Gemini. All models exhibited systematic underestimation that increased with portion size, with bias slopes ranging from -0.23 to -0.50.

Conclusions

ChatGPT and Claude achieved accuracy levels comparable with traditional self-reported dietary assessment methods but without associated user burden, suggesting potential utility as dietary monitoring tools. However, systematic underestimation of large portions and high variability in macronutrient estimation indicate these general-purpose LLMs are not yet suitable for precise dietary assessment in clinical or athletic populations where accurate quantification is critical.

Schlagwörter

Stichwörter der Autor:innen

ChatGPTClaudeGeminiartificial intelligencedietary assessmentlarge language modelvalidation study

Autor:innen und Institutionen

  • Center for Lifestyle Intervention, Institute of Medicine, University of Gothenburg, Gothenburg, Sweden.
  • Department of Medicine Geriatrics and Emergency Medicine Östra, Sahlgrenska University Hospital, Gothenburg, Sweden.
  • Center for Health and Performance, Department of Food and Nutrition and Sport Science, University of Gothenburg, Gothenburg, Sweden.

Zitieren

APA

Fridolfsson, J., Sjöberg, E., Thiwång, M., & Pettersson, S. (2025). Performance Evaluation of 3 Large Language Models for Nutritional Content Estimation from Food Images. Current Developments in Nutrition, 9(10), 107556. https://doi.org/10.1016/j.cdnut.2025.107556

Vancouver

Fridolfsson J, Sjöberg E, Thiwång M, Pettersson S. Performance Evaluation of 3 Large Language Models for Nutritional Content Estimation from Food Images. Current Developments in Nutrition. 2025;9(10):107556. doi:10.1016/j.cdnut.2025.107556

BibTeX
@article{Fridolfsson2025,
  author = {Fridolfsson, Jonatan and Sjöberg, Emma and Thiwång, Meri and Pettersson, Stefan},
  title = {Performance Evaluation of 3 Large Language Models for Nutritional Content Estimation from Food Images},
  journal = {Current Developments in Nutrition},
  year = {2025},
  volume = {9},
  number = {10},
  pages = {107556},
  doi = {10.1016/j.cdnut.2025.107556}
}
Kostenlos starten →