NAct: The Nutrition &amp; Activity Ontology for Healthy Living

Tsatsou, Dorothea; Lalama, Elena; Wilson-Barnes, Saskia; Hart, Kathryn; Cornelissen, Véronique; Buys, Roselien; Pagkalos, Ioannis; Dias, Sofia B.; Dimitropoulos, Kosmas; Daras, Petros

doi:10.3233/faia210377

Cited by 6 publications

(10 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is hoped that future tools will consider harnessing a similar methodology to that presented here. The nutrition and activity ontology (NAct), NAP database, user requirements and evaluation survey are all publicly available datasets on GitHub Tsatsou et al (2021) and Zenodo Community (2024) respectively. Future research is encouraged to incorporate tailored advice according to genetic predisposition, where the evidence base supports this, to provide food equivalents for meal recipes to increase variety and to ensure the underpinning advice continues to represent the state of the art in the relevant country and/or population group.…”

Section: Discussionmentioning

confidence: 99%

The development of an EU‐wide nutrition and physical activity expert knowledge base to support a personalised mobile application across various EU population groups

Wilson‐Barnes,

Pagkalos,

Patra

et al. 2024

Nutrition Bulletin

View full text Add to dashboard Cite

A healthy lifestyle comprising regular physical activity and an adequate diet is imperative for the prevention of non‐communicable diseases such as hypertension and some cancers. Advances in information computer technology offer the opportunity to provide personalised lifestyle advice directly to the individual through devices such as smartphones or tablets. The overall aim of the PROTEIN project (Wilson‐Barnes et al., 2021) was to develop a smartphone application that could provide tailored and dynamic nutrition and physical activity advice directly to the individual in real time. However, to create this mobile health (m‐health) smartphone application, a knowledge base of reference ranges for macro‐/micronutrient intake, anthropometry, biochemical, physiological and sleep parameters was required to underpin the parameters of the recommender systems. Therefore, the principal aim of this emerging research paper is to describe the process by which experts in nutrition and physiology from the PROTEIN consortium collaborated to develop the nutritional and physical activity requirements, based upon existing recommendations, for 10 separate population groups living within the EU including, but not limited to healthy adults, adults with type 2 diabetes mellitus, cardiovascular disease, excess weight, obesity and iron deficiency anaemia. A secondary aim is to describe the development of a library of 24‐h meal plans appropriate for the same groups and also encompassing various dietary preferences and allergies. Overall, the consortium devised an extensive nutrition and physical activity knowledge base that is pertinent to 10 separate EU user groups, is available in 7 different languages and is practically implemented via a library of culturally appropriate, 24‐h meal plans.

show abstract

Section: Discussionmentioning

confidence: 99%

The development of an EU‐wide nutrition and physical activity expert knowledge base to support a personalised mobile application across various EU population groups

Wilson‐Barnes,

Pagkalos,

Patra

et al. 2024

Nutrition Bulletin

View full text Add to dashboard Cite

show abstract

“…The latter was created based on experts' knowledge from the fields of nutrition, activity, and health fields. In NAct ontology, each subject's implicit/explicit goals related to nutrition and well-being are connected with his/her situational condition and standardized European nutritional and well-being directives ( 117 ). Overall, the NAct ontology models: i) in a slim and holistic manner food-specific nutritional information and activity-specific well-being information; ii) nutritional and well-being user goals and relates them with nutritional and well-being information; iii) medical conditions, allergies, intolerances, deficiencies, and lifestyle dietary choices and relates them with nutritional and well-being information; and iv) properties that define specificities of the aforementioned relationships that aid in the selection of appropriate meals and physical activities for a given person.…”

Section: Discussionmentioning

confidence: 99%

Users' Perspective on the AI-Based Smartphone PROTEIN App for Personalized Nutrition and Healthy Living: A Modified Technology Acceptance Model (mTAM) Approach

et al. 2022

Self Cite

View full text Add to dashboard Cite

The ubiquitous nature of smartphone ownership, its broad application and usage, along with its interactive delivery of timely feedback are appealing for health-related behavior change interventions via mobile apps. However, users' perspectives about such apps are vital in better bridging the gap between their design intention and effective practical usage. In this vein, a modified technology acceptance model (mTAM) is proposed here, to explain the relationship between users' perspectives when using an AI-based smartphone app for personalized nutrition and healthy living, namely, PROTEIN, and the mTAM constructs toward behavior change in their nutrition and physical activity habits. In particular, online survey data from 85 users of the PROTEIN app within a period of 2 months were subjected to confirmatory factor analysis (CFA) and regression analysis (RA) to reveal the relationship of the mTAM constructs, i.e., perceived usefulness (PU), perceived ease of use (PEoU), perceived novelty (PN), perceived personalization (PP), usage attitude (UA), and usage intention (UI) with the users' behavior change (BC), as expressed via the acceptance/rejection of six related hypotheses (H1–H6), respectively. The resulted CFA-related parameters, i.e., factor loading (FL) with the related p-value, average variance extracted (AVE), and composite reliability (CR), along with the RA results, have shown that all hypotheses H1–H6 can be accepted (p < 0.001). In particular, it was found that, in all cases, FL > 0.5, CR > 0.7, AVE > 0.5, indicating that the items/constructs within the mTAM framework have good convergent validity. Moreover, the adjusted coefficient of determination (R2) was found within the range of 0.224–0.732, justifying the positive effect of PU, PEoU, PN, and PP on the UA, that in turn positively affects the UI, leading to the BC. Additionally, using a hierarchical RA, a significant change in the prediction of BC from UA when the UI is used as a mediating variable was identified. The explored mTAM framework provides the means for explaining the role of each construct in the functionality of the PROTEIN app as a supportive tool for the users to improve their healthy living by adopting behavior change in their dietary and physical activity habits. The findings herein offer insights and references for formulating new strategies and policies to improve the collaboration among app designers, developers, behavior scientists, nutritionists, physical activity/exercise physiology experts, and marketing experts for app design/development toward behavior change.

show abstract

“…More specifically, the advisor consists of two components, the Reasoning-based Decision Support System (RDSS) and the NP generation component. The RDSS generates the set of appropriate meals for a user based on user profile information, the set of available meals, and an ontology of qualitative rules acquired from Nutrition experts [ 41 ]. The NP generation component combines the appropriate meals to form daily meal plans for recommendation.…”

Section: Methodsmentioning

confidence: 99%

“…Therefore, the Nutrition and Activity (NAct) ontology [ 41 ] was developed as an integral part of the PROTEIN project, serving as the reference knowledge base of the Reasoning-based Decision Support System (RDSS) component of the AI advisor. Previous research yielded several key European and International food and nutrient databases complete with few pre-existing nutritional ontologies, which do not account for rules or relationships between foods/nutrients and user circumstances (diets and/or conditions).…”

Section: Methodsmentioning

confidence: 99%

“…In this work, an AI-based nutritional advisor is proposed that can be categorized as a knowledge-based recommender system for meal plans. The proposed nutritional advisor initially takes into consideration user information such as age, sex, weight, height, dietary choices, health conditions and preferences and identifies a list of appropriate meals that satisfy the personalized nutritional needs of the specific user through a powerful ontology of nutritional rules [ 41 ]. This was defined by experts in nutrition and physiology and is in accordance with the European Food Safety Authority (EFSA) recommendations on nutrition.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

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

et al. 2022

View full text Add to dashboard Cite

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.

show abstract

NAct: The Nutrition & Activity Ontology for Healthy Living

Cited by 6 publications

References 15 publications

The development of an EU‐wide nutrition and physical activity expert knowledge base to support a personalised mobile application across various EU population groups

The development of an EU‐wide nutrition and physical activity expert knowledge base to support a personalised mobile application across various EU population groups

Users' Perspective on the AI-Based Smartphone PROTEIN App for Personalized Nutrition and Healthy Living: A Modified Technology Acceptance Model (mTAM) Approach

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

Contact Info

Product

Resources

About