DietBot: AI-based personalized nutritional advice generated from individual health parameters and food purchase behavior

You are unique! And thus, your diet should be unique to you too! Nutrition is an important determinant of health, especially given the rising numbers of overweight and obese people, and the rise of lifestyle-related diseases.

The DietBot project aims to make measuring dietary intake and providing personal dietary advice fully automated. DietBot will read your receipts, calculate your food intake and, based on this information, provide an individualized nutrition plan customized to your current individual health status, dietary habits and preferences. We will work with modular methods, so that we can keep adding new functionalities to increase the accuracy of the data collection and improve the quality of the generated advice.

This project will be performed by the Division of Human Nutrition & Health and Wageningen Food & Biobased Research from Wageningen University & Research.

Food-health relations

Nutritional guidelines merely differentiate between different age categories, gender, vegan/vegetarian preferences and being pregnant/lactating or not. There is a big variation in individual responses to food intake and individuals also vary in their risk profiles for nutrition-related diseases. Therefore, providing dietary advice on an individual level may lead to more health benefits.

Current guidance of patients is usually done by dietitians and other healthcare professionals. Digitalized guidance can significantly extend the reach and impact of dietitians. In fact, there are many apps available that want to help consumers eat healthier. However, the advice given by these apps is usually based on generalized recommendations.

The research aim for this project is to further personalize dietary advice with the help of knowledge on relationships between food intake and individual health parameters that are grounded in science. For example, based on the individual measurement of BMI, blood pressure, cholesterol level and an increased risk of heart failure, the advice can be to pay particular attention to eating less saturated fat and eating more of specific vegetables.

Making knowledge accessible

We would like to research how to combine this data with the already available services in our personalized dietary advice platform to generate customized replacers for food products in a person’s diet. Secondly, we would like to investigate methods to make registering food intake data user friendly, e.g., by uploading personal purchasing data.

The above-described project is being developed for application to the NWO Open Technology Program, a Dutch governmental program sponsoring applied research. Aiming for 5-6 partners to participate in an advisory board.

This advisory board is open for participation from food companies and software companies interested in the nutrition and health domain. In return for their contributions to the project, partners can provide directions to the research activities and be the first to be informed about the results.

Unfortunately, we are not able to reply to solicitations from research institutes or enquiries from students related to this project.