FoodCoach: Fully Automated Diet Counseling

Jing Wu, Simon Mayer, Simeon Pilz, Yasmine Sheila Antille, Jan Liam Albert, Melanie Stoll, Kimberly García, Klaus Ludwig Fuchs, Lia Bally, Lukas Eichelberger, Tanja Schneider, Verena Tiefenbeck, Sybilla Merian, Freya Orban

Abstract: Unhealthy dietary habits are a major preventable risk factor for widespread non-communicable diseases (NCDs). Diet counseling is effective in managing diet-related NCDs, but constrained by its manual nature and limited (clinical) resources. To address these challenges, we propose FoodCoach, a fully automated diet counseling system that monitors people's food purchases using digital receipts from loyalty cards and provides structured dietary recommendations. We introduce the FoodCoach system's dietary recommender algorithm and architecture, alongside evaluation results from a two-arm randomized controlled trial involving 61 participants. The trial results demonstrate the technical feasibility and potential for scalable, fully automated diet counseling, despite not showing a significant change in participants' food purchase healthiness. We further show how to deploy and extend the FoodCoach system in new contexts, provide all relevant source code, and discuss how to verify and enhance the system efficacy. Our core research contributions are: 1) a novel dietary recommender algorithm designed and implemented with clinical nutritional experts, and 2) a scalable system architecture that employs a knowledge graph for enhanced interoperability and applicability to diverse domains and data sources. From a practical perspective, FoodCoach can augment clinical diet counseling through novel insights about patient food purchases and continuous support between consultations. Its cost-effective automated recommendations can also benefit the general public by helping combat NCD.

External IDs:dblp:journals/titb/WuMPAASGFBESTMO25