NutriWell: An Explainable Ontology-Based FoodAI Service for Nutrition and Health Management

Non-communicable diseases (NCDs) like hypertension, diabetes, osteoporosis, and cancer constitute 80% of the disease burden in European countries, affecting a significant portion of the working-age population. Addressing these numbers requires a strong effort in prevention and management. Nutrition is crucial not only for chronic conditions but also for non-chronic medical needs such as pregnancy, allergies, and intolerances. Artificial Intelligence (AI), especially when integrated with chatbots or social robots, now plays a pivotal role in assisting users with NCD prevention and management, as well as dietary needs. This manuscript introduces NutriWell, a framework leveraging AI and the GraphBRAIN technology for intelligent knowledge retrieval in nutrition and health management. NutriWell informs users about meal suitability based on their nutritional requirements, utilizing explanations that combine feature data and user preferences. Italian websites such as GialloZafferano and AlimentiNUTrizione provide extensive catalogs of European meals, including ingredients, allergens, and dietary specifics. The contribution of this work is the construction of a personalized diet assistant by utilizing datasets extracted from these websites that, as far as we know, have never been used for these tasks. A key contribution is an API that retrieves graph-based information integrated with an ontology specifying relational constraints. The ontology design, derived from existing frameworks and enhanced to integrate food impacts on disorders, allows for the calculation of meal impact scores tailored to user needs and preferences.