JMIR Publications

ABSTRACT

Current health status of the general public can significantly benefit from a healthier diet. Using a personalized approach to initiate healthier dietary behavior seems a promising strategy, since individuals differ in terms of health status and subsequent dietary needs as well as their desired behavior change support. However, giving personalized advice to a wide audience over a longer period of time is very labor intensive. This bottleneck can possibly be overcome by digitalizing the process of creating and giving personalized advice. More and more personalized advice systems for different purposes are becoming available on the market ranging from systems providing advice on just a single parameter to very complex systems which include many variables characterizing each individual situation. Scientific background is often lacking in these systems. In designing a personalized nutrition advice system, many design questions need to be answered, ranging from required input parameters and accurate measurement methods (sense), type of modelling techniques to be used (reason), and the modality in which the personalized advice is given (act). We address these topics in our paper, and we have demonstrated the feasibility of setting up an infrastructure for giving personalized dietary advice based on the experience of two practical applications in a real-life setting.