JMIR Publications

ABSTRACT

Background:

Personalised dietary advice needs to consider the individual’s health risks as well as specific food preferences, offering healthier options aligned with personal tastes.

Objective:

This study aims to develop a Digital Health Intervention (DHI) that provides personalised nutrition recommendations based on individual food preference profiles, and utilising data from the UK Biobank.

Methods:

Data from 61,229 UK Biobank participants were used to develop a conceptual pipeline of digital health interventions. The pipeline included three steps: (1) developing a simplified food preference profiling tool; (2) creating a Cardiovascular Disease (CVD) prediction model for subsequent profiles; and (3) selecting intervention features. The CVD prediction model was created using three different predictor sets (Framingham set, diet set, and food preference profile set) across four machine learning models (logistic regression, linear discriminant analysis, random forest, and support vector machine). Intervention functions were designed using the Behaviour Change Wheel tool, and behaviour change techniques were selected for the DHI features.

Results:

Feature selection process identified 14 food items out of 140 that effectively classify food preference profiles. The food preference profile prediction set, which did not include blood measurements and detailed nutrient intake, demonstrated comparable accuracy (across the four models: 0.721 to 0.725) to the Framingham set (0.724 to 0.727) and diet set (0.722 to 0.725). Linear Discriminant Analysis was chosen as the best model. Four key features of the DHI were identified: food source and portion information, recipes, dietary recommendation system, and community exchange platforms. The food preference profile and CVD risk prediction model serve as input feeds for the dietary recommendation system. Two levels of personalised nutrition advice were proposed: Level 1 - based on food portion intake and food preference profile; Level 2 - based on nutrient intake, food preference profile, and CVD risk probability.

Conclusions:

This study is proof of principle for a conceptual pipeline for a DHI that empowers users to make informed dietary choices, and reduce CVD risk by catering to person-specific needs and preferences. By making healthy eating more accessible and sustainable, the DHI has the potential to significantly impact public health outcomes.