Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients
Nutrients · 29.04.2025 · 17 (9) · 1492
DOI: 10.3390/nu17091492 ↗Kurz gefasst
Fachartikel in der Zeitschrift Nutrients, online erschienen am 29.04.2025. Verfasst von Leon Kopitar und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia. Hauptthemen laut MEDLINE: Meals, Food Ingredients. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Union's Horizon Europe, European Union’s Horizon Europe research and innovation programme.
Abstract (Originalsprache)
Background/Objectives: Identifying and decomposing compound ingredients within meal plans presents meal customization and nutritional analysis challenges. It is essential for accurately identifying and replacing problematic ingredients linked to allergies or intolerances and helping nutritional evaluation.
Methods
This study explored the effectiveness of three large language models (LLMs)—GPT-4o, Llama-3 (70B), and Mixtral (8x7B), in decomposing compound ingredients into basic ingredients within meal plans. GPT-4o was used to generate 15 structured meal plans, each containing compound ingredients. Each LLM then identified and decomposed these compound items into basic ingredients. The decomposed ingredients were matched to entries in a subset of the USDA FoodData Central repository using API-based search and mapping techniques. Nutritional values were retrieved and aggregated to evaluate accuracy of decomposition. Performance was assessed through manual review by nutritionists and quantified using accuracy and F1-score. Statistical significance was tested using paired t-tests or Wilcoxon signed-rank tests based on normality.
Results
Results showed that large models—both Llama-3 (70B) and GPT-4o—outperformed Mixtral (8x7B), achieving average F1-scores of 0.894 (95% CI: 0.84–0.95) and 0.842 (95% CI: 0.79–0.89), respectively, compared to an F1-score of 0.690 (95% CI: 0.62–0.76) from Mixtral (8x7B).
Conclusions
The open-source Llama-3 (70B) model achieved the best performance, outperforming the commercial GPT-4o model, showing its superior ability to consistently break down compound ingredients into precise quantities within meal plans and illustrating its potential to enhance meal customization and nutritional analysis. These findings underscore the potential role of advanced LLMs in precision nutrition and their application in promoting healthier dietary practices tailored to individual preferences and needs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Faculty of Health Sciences, University of Maribor, 2000 Maribor, Slovenia.
- Faculty of Electrical Engineering and Computer Science, University of Maribor, 2000 Maribor, Slovenia.
- The Nu B.V., 2333 CH Leiden, The Netherlands.
- Pain Research & Intervention Center of Excellence (PRICE), University of Florida, Gainesville, FL 32608, USA.
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL 32608, USA.
- Department of Biostatistics and Health Data Science, Indiana University, Bloomington, IN 46202, USA.
ORCID-Profile: Leon Kopitar, Leon Bedrač, Larissa J Strath, Jiang Bian, Gregor Stiglic
Förderung
- European Union's Horizon Europe
- European Union’s Horizon Europe research and innovation programme
Zitieren
APA
Kopitar, L., Bedrač, L., Strath, L. J., Bian, J., & Stiglic, G. (2025). Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients. Nutrients, 17(9), 1492. https://doi.org/10.3390/nu17091492
Vancouver
Kopitar L, Bedrač L, Strath LJ, Bian J, Stiglic G. Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients. Nutrients. 2025;17(9):1492. doi:10.3390/nu17091492
BibTeX
@article{Kopitar2025,
author = {Kopitar, Leon and Bedrač, Leon and Strath, Larissa J and Bian, Jiang and Stiglic, Gregor},
title = {Improving Personalized Meal Planning with Large Language Models: Identifying and Decomposing Compound Ingredients},
journal = {Nutrients},
year = {2025},
volume = {17},
number = {9},
pages = {1492},
doi = {10.3390/nu17091492}
}
EUVIMED