This study aims to evaluate the effectiveness of an artificial intelligence (AI)-supported, context-aware digital nudging intervention designed to reduce ultra-processed food consumption and improve dietary sustainability among adolescents and young adults. The intervention utilizes real-time behavioral data, including image-assisted dietary logging and contextual information, to identify high-risk consumption moments and deliver personalized, non-coercive nudges. The study will assess changes in ultra-processed food intake, contextual consumption patterns, and sustainability-related dietary indicators.
This study investigates the effectiveness of an artificial intelligence (AI)-supported, context-aware digital intervention targeting ultra-processed food (UPF) consumption among adolescents and young adults. UPF consumption has been identified as a major contributor to non-communicable diseases and is associated with significant environmental impacts. However, existing digital nutrition interventions largely rely on static, nutrient-based approaches and do not adequately capture real-life behavioral contexts. The intervention integrates image-assisted dietary logging, contextual data collection (including time, location, and social setting), and explainable artificial intelligence to identify high-risk moments of UPF consumption. Based on these insights, the system delivers adaptive, personalized digital nudges designed to support healthier and more sustainable food choices without restricting user autonomy. The study follows a controlled evaluation design to assess the effectiveness of the intervention. Primary outcomes include changes in context-specific UPF consumption patterns, while secondary outcomes include overall dietary quality, sustainability-related indicators (such as environmental impact proxies), and user engagement metrics. This research aims to provide evidence for scalable, ethically governed digital health interventions that integrate behavioral science, nutrition, and sustainability within real-life settings
Study Type
INTERVENTIONAL
Allocation
NON_RANDOMIZED
Purpose
PREVENTION
Masking
NONE
Enrollment
1,000
A context-aware digital intervention delivering personalized nudges based on real-time dietary behavior and contextual data to reduce ultra-processed food consumption.
Change in ultra-processed food consumption (servings per day)
Change in ultra-processed food consumption, expressed as servings per day, assessed using dietary intake data collected via a digital dietary assessment platform (food diary-based tracking system). Consumption will be quantified based on reported frequency and portion size.
Time frame: From baseline to 10 months and 20 months
Change in frequency of ultra-processed food consumption (times per day)
Change in the frequency of ultra-processed food consumption, expressed as times per day, assessed using a digital dietary tracking platform (food diary-based system).
Time frame: From baseline to 10 months and 20 months
Change in proportion of ultra-processed food consumption (% of total intake)
Change in the proportion of ultra-processed food consumption, expressed as percentage of total dietary intake, derived from dietary tracking data collected via a digital dietary assessment platform.
Time frame: From baseline to 10 months and 20 months
Change in temporal eating patterns (eating occasions per day and timing)
Change in temporal eating patterns, including number of eating occasions per day and timing of meals, assessed using time-stamped dietary records collected via a digital dietary tracking platform.
Time frame: From baseline to 10 months and 20 months
Change in context-specific dietary behaviours (categorical variables)
Change in context-specific dietary behaviours, including eating location and social context, assessed as categorical variables using data recorded via a digital dietary tracking platform.
Time frame: From baseline to 10 months and 20 months
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.