EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

An Evaluation of ChatGPT for Nutrient Content Estimation from Meal Photographs

Cathal O'Hara iD, Gráinne Kent, Angela C Flynn, Eileen R Gibney iD, Claire M Timon iD

Nutrients · 07.02.2025 · 17 (4) · 607

DOI: 10.3390/nu17040607 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Nutrients, online erschienen am 07.02.2025. Verfasst von Cathal O'Hara und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Population Health, Royal College of Surgeons in Ireland (RCSI), D02 YN77 Dublin, Ireland. Hauptthemen laut MEDLINE: Photography, Meals, Nutritive Value, Nutrients. Die Arbeit wurde bisher 48-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background/Objectives: Advances in artificial intelligence now allow combined use of large language and vision models; however, there has been limited evaluation of their potential in dietary assessment. This study aimed to evaluate the accuracy of ChatGPT-4 in estimating nutritional content of commonly consumed meals using meal photographs derived from national dietary survey data.

Methods

Meal photographs (n = 114) were uploaded to ChatGPT and it was asked to identify the foods in each meal, estimate their weight, and estimate the nutrient content of the meals for 16 nutrients for comparison with the known values using precision, paired t-tests, Wilcoxon signed rank test, percentage difference, and Spearman correlation (rs). Seven dietitians also estimated energy, protein, and carbohydrate content of thirty-eight meal photographs for comparison with ChatGPT using intraclass correlation (ICC).

Results

Comparing ChatGPT and actual meals, ChatGPT showed good precision (93.0%) for correctly identifying the foods in the photographs. There was good agreement for meal weight (p = 0.221) for small meals, but poor agreement for medium (p < 0.001) and large (p < 0.001) meals. There was poor agreement for 10 of the 16 nutrients (p < 0.05). Percentage difference from actual values was >10% for 13 nutrients, with ChatGPT underestimating 11 nutrients. Correlations were adequate or good for all nutrients with rs ranging from 0.29 to 0.83. When comparing ChatGPT and dietitians, the ICC ranged from 0.31 to 0.67 across nutrients.

Conclusions

ChatGPT performed well for identifying foods, estimating weights of small portion sizes, and ranking meals according to nutrient content, but performed poorly for estimating weights of medium and large portion sizes and providing accurate estimates of nutrient content.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotographyMealsNutritive ValueNutrientsNutrition AssessmentArtificial IntelligenceHumansDiet SurveysReproducibility of ResultsGenerative Artificial Intelligence

Stichwörter der Autor:innen

computer visiondietary intake assessmentfood compositiongenerative artificial intelligenceimage-based dietary intake assessmentlarge language models

Substanzen

Nutrients

Autor:innen und Institutionen

  • School of Population Health, Royal College of Surgeons in Ireland (RCSI), D02 YN77 Dublin, Ireland.
  • UCD Institute of Food and Health, University College Dublin, D04 V1W8 Dublin, Ireland.
  • School of Agriculture and Food Science, University College Dublin, D04 V1W8 Dublin, Ireland.

ORCID-Profile: Cathal O'Hara, Eileen R Gibney, Claire M Timon

Zitieren

APA

O'Hara, C., Kent, G., Flynn, A. C., Gibney, E. R., & Timon, C. M. (2025). An Evaluation of ChatGPT for Nutrient Content Estimation from Meal Photographs. Nutrients, 17(4), 607. https://doi.org/10.3390/nu17040607

Vancouver

O'Hara C, Kent G, Flynn AC, Gibney ER, Timon CM. An Evaluation of ChatGPT for Nutrient Content Estimation from Meal Photographs. Nutrients. 2025;17(4):607. doi:10.3390/nu17040607

BibTeX
@article{OHara2025,
  author = {O'Hara, Cathal and Kent, Gráinne and Flynn, Angela C and Gibney, Eileen R and Timon, Claire M},
  title = {An Evaluation of ChatGPT for Nutrient Content Estimation from Meal Photographs},
  journal = {Nutrients},
  year = {2025},
  volume = {17},
  number = {4},
  pages = {607},
  doi = {10.3390/nu17040607}
}
Kostenlos starten →