Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2022 Oct 21;14(20):4435.
doi: 10.3390/nu14204435.

PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets

Kiriakos Stefanidis  1 , Dorothea Tsatsou  1 , Dimitrios Konstantinidis  1 , Lazaros Gymnopoulos  1 , Petros Daras  1 , Saskia Wilson-Barnes  2 , Kathryn Hart  2 , Véronique Cornelissen  3 , Elise Decorte  3 , Elena Lalama  4 , Andreas Pfeiffer  4 , Maria Hassapidou  5 , Ioannis Pagkalos  5 , Anagnostis Argiriou  6 , Konstantinos Rouskas  6 , Stelios Hadjidimitriou  7 , Vasileios Charisis  7 , Sofia Balula Dias  8 , José Alves Diniz  8 , Gonçalo Telo  9 , Hugo Silva  9 , Alex Bensenousi  10 , Kosmas Dimitropoulos  1
Affiliations

PROTEIN AI Advisor: A Knowledge-Based Recommendation Framework Using Expert-Validated Meals for Healthy Diets

Kiriakos Stefanidis et al. Nutrients. .

Abstract

AI-based software applications for personalized nutrition have recently gained increasing attention to help users follow a healthy lifestyle. In this paper, we present a knowledge-based recommendation framework that exploits an explicit dataset of expert-validated meals to offer highly accurate diet plans spanning across ten user groups of both healthy subjects and participants with health conditions. The proposed advisor is built on a novel architecture that includes (a) a qualitative layer for verifying ingredient appropriateness, and (b) a quantitative layer for synthesizing meal plans. The first layer is implemented as an expert system for fuzzy inference relying on an ontology of rules acquired by experts in Nutrition, while the second layer as an optimization method for generating daily meal plans based on target nutrient values and ranges. The system's effectiveness is evaluated through extensive experiments for establishing meal and meal plan appropriateness, meal variety, as well as system capacity for recommending meal plans. Evaluations involved synthetic data, including the generation of 3000 virtual user profiles and their weekly meal plans. Results reveal a high precision and recall for recommending appropriate ingredients in most user categories, while the meal plan generator achieved a total recommendation accuracy of 92% for all nutrient recommendations.

Keywords: artificial intelligence; meal plan recommendations; ontology; personalized nutrition.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Architecture of the AI-based nutritional advisor.
Figure 2
Figure 2
Birds-eye view of the NAct Ontology, v1.9.5, with over 750 interconnected classes.
Figure 3
Figure 3
NP creation rate for virtual user profiles with (a) at least the condition(s) mentioned, and (b) exactly the condition(s) mentioned (first experiment).
Figure 4
Figure 4
NP creation rate for virtual user profiles with (a) at least the condition(s) mentioned, and (b) exactly the condition(s) mentioned (second experiment).
Figure 5
Figure 5
Examples of meal options for breakfast, lunch, afternoon snack and dinner, available in the database of meals.
Figure 6
Figure 6
Bland-Altman plots depicting energy intake differences for each user group.
Figure 7
Figure 7
Distribution of energy intake differences between recommended and target values.
Figure 8
Figure 8
Average meal variety for each meal type in a generated weekly meal plan.
Figure 9
Figure 9
Distribution of meal variety across users.
See this image and copyright information in PMC

References

    1. World Health Organization Noncommunicable Diseases. [(accessed on 13 September 2022)];2021 Available online: https://www.who.int/news-room/fact-sheets/detail/noncommunicable-diseases.
    1. Dernini S., Berry E.M. Mediterranean diet: From a healthy diet to a sustainable dietary pattern. Front. Nutr. 2015;2:15. doi: 10.3389/fnut.2015.00015. - DOI - PMC - PubMed
    1. Gibney M.J., Walsh M.C. The future direction of personalised nutrition: My diet, my phenotype, my genes. Proc. Nutr. Soc. 2013;72:219–225. doi: 10.1017/S0029665112003436. - DOI - PubMed
    1. Wickramasinghe K., Mathers J.C., Wopereis S., Marsman D.S., Griffiths J.C. From lifespan to healthspan: The role of nutrition in healthy ageing. J. Nutr. Sci. 2020;9:E33. doi: 10.1017/jns.2020.26. - DOI - PMC - PubMed
    1. Picó C., Serra F., Rodríguez A.M., Keijer J., Palou A. Biomarkers of nutrition and health: New tools for new approaches. Nutrients. 2019;11:1092. doi: 10.3390/nu11051092. - DOI - PMC - PubMed

LinkOut - more resources