View in EDS

NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence.

Saved in:
Bibliographic Details
Title: NutriGen: Personalized Meal Plan Generator Leveraging Large Language Models to Enhance Dietary and Nutritional Adherence.
Authors: Khamesian S, Arefeen A, Carpenter SM, Ghasemzadeh H
Source: Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference [Annu Int Conf IEEE Eng Med Biol Soc] 2025 Jul; Vol. 2025, pp. 1-7.
Publication Type: Journal Article
Language: English
Journal Info: Publisher: [IEEE] Country of Publication: United States NLM ID: 101763872 Publication Model: Print Cited Medium: Internet ISSN: 2694-0604 (Electronic) Linking ISSN: 23757477 NLM ISO Abbreviation: Annu Int Conf IEEE Eng Med Biol Soc Subsets: MEDLINE
Imprint Name(s): Original Publication: [Piscataway, NJ] : [IEEE], [2007]-
MeSH Terms: Meals* , Diet* , Precision Medicine* , Language* , Programming Languages*, Humans ; Databases, Factual ; Large Language Models
Abstract: Maintaining a balanced diet is essential for overall health, yet many individuals struggle with meal planning due to nutritional complexity, time constraints, and lack of dietary knowledge. Personalized food recommendations can help address these challenges by tailoring meal plans to individual preferences, habits, and dietary restrictions. However, existing dietary recommendation systems often lack adaptability, fail to consider real-world constraints such as food ingredient availability, and require extensive user input, making them impractical for sustainable and scalable daily use. To address these limitations, we introduce NutriGen, a framework based on large language models (LLM) designed to generate personalized meal plans that align with user-defined dietary preferences and constraints. By building a personalized nutrition database and leveraging prompt engineering, our approach enables LLMs to incorporate reliable nutritional references like the USDA nutrition database while maintaining flexibility and ease-of-use. We demonstrate that LLMs have strong potential in generating accurate and user-friendly food recommendations, addressing key limitations in existing dietary recommendation systems by providing structured, practical, and scalable meal plans. Our evaluation shows that Llama 3.1 8B and GPT-3.5 Turbo achieve the lowest percentage errors of 1.55% and 3.68%, respectively, producing meal plans that closely align with user-defined caloric targets while minimizing deviation and improving precision. Additionally, we compared the performance of DeepSeek V3 against several established models to evaluate its potential in personalized nutrition planning. Our results showed that it struggled with accuracy, exhibiting a higher MAE of 10.45%, and was significantly slower in processing time compared to models like GPT-3.5 Turbo and Llama 3.1 8B, highlighting the need for further optimization.
Entry Date(s): Date Created: 20251203 Date Completed: 20251203 Latest Revision: 20251203
Update Code: 20260130
DOI: 10.1109/EMBC58623.2025.11253879
PMID: 41337241
Database: MEDLINE
Description
Abstract:Maintaining a balanced diet is essential for overall health, yet many individuals struggle with meal planning due to nutritional complexity, time constraints, and lack of dietary knowledge. Personalized food recommendations can help address these challenges by tailoring meal plans to individual preferences, habits, and dietary restrictions. However, existing dietary recommendation systems often lack adaptability, fail to consider real-world constraints such as food ingredient availability, and require extensive user input, making them impractical for sustainable and scalable daily use. To address these limitations, we introduce NutriGen, a framework based on large language models (LLM) designed to generate personalized meal plans that align with user-defined dietary preferences and constraints. By building a personalized nutrition database and leveraging prompt engineering, our approach enables LLMs to incorporate reliable nutritional references like the USDA nutrition database while maintaining flexibility and ease-of-use. We demonstrate that LLMs have strong potential in generating accurate and user-friendly food recommendations, addressing key limitations in existing dietary recommendation systems by providing structured, practical, and scalable meal plans. Our evaluation shows that Llama 3.1 8B and GPT-3.5 Turbo achieve the lowest percentage errors of 1.55% and 3.68%, respectively, producing meal plans that closely align with user-defined caloric targets while minimizing deviation and improving precision. Additionally, we compared the performance of DeepSeek V3 against several established models to evaluate its potential in personalized nutrition planning. Our results showed that it struggled with accuracy, exhibiting a higher MAE of 10.45%, and was significantly slower in processing time compared to models like GPT-3.5 Turbo and Llama 3.1 8B, highlighting the need for further optimization.
ISSN:2694-0604
DOI:10.1109/EMBC58623.2025.11253879