Peer-reviewed article
Causal machine learning for understanding heterogeneous effects of childhood obesity prevention
Nu Hoang, Toan K Nguyen, Bao Duong, Melanie Nichols, Vicki Brown et al. ·
Summary
Written by AI, not yet AICS's view · claude-sonnet-5-5This paper proposes a way of using causal machine learning to see how the effects of community-based childhood obesity prevention programs differ between children. It uses data from seven programs with more than 7000 participants. The analysis found links between body mass index (BMI), age, sex and eating habits such as takeaway food consumption. Effects of the programs differed across children, and age was an important factor in how well they worked. The authors suggest this could help design more targeted, age-sensitive prevention programs.
Key points
- Data came from seven community-based intervention programs with more than 7000 participants.
- Causal discovery found links between BMI, age, sex and dietary behaviours such as takeaway food consumption.
- Estimated individual treatment effects differed notably between participants.
- Age emerged as an important moderator of how effective the programs were.
- The authors say the framework could be used to analyse varying effects in other complex community-based interventions.
Limitations
The abstract does not describe the study design (for example, whether there were comparison groups), the size of the effects, or the age groups involved. The country is not stated in the abstract, only in the metadata hint. The main contribution is a method, so it does not show that any specific intervention works.
Abstract
Abstract Community-based interventions (CBIs) are widely used to prevent childhood obesity, yet evaluating their causal effects is challenging due to multi-level interactions and variation across individuals. Standard statistical approaches often have difficulty addressing these complexities, which can produce biased estimates. To address this, we propose a causal machine learning framework that integrates causal discovery, causal inference, and tree-based models to estimate individual treatment effects and examine heterogeneity in program outcomes. Using data from seven CBI programs involving more than 7000 participants, we first applied causal discovery to identify relationships between children’s demographic and behavioral characteristics, finding links between body mass index (BMI), age, sex, and dietary behaviors such as takeaway food consumption. Individual treatment effect estimation suggested notable differences in intervention outcomes across participants, with age emerging as an important moderator of effectiveness. Tree-based models further highlighted subpopulation characteristics associated with these variations. Our findings suggest that CBI effectiveness is not uniform across children, and that identifying sources of heterogeneity can support the design of more targeted and age-sensitive prevention strategies. While demonstrated here in the context of childhood obesity, the framework provides a generalizable approach for analyzing heterogeneous treatment effects in complex, community-based interventions.
Findings the Hub has extracted
Each claim below is labelled by its type of design and links back to this report.
- Intervention
- Community-based childhood obesity prevention programs, analysed with a causal machine learning framework (causal discovery, causal inference and tree-based models) to estimate individual treatment effects.
- Population
- More than 7000 children participating in seven community-based intervention programs.
Key finding
Individual treatment effects suggested notable differences in outcomes across participants.
Hoang et al. · OpenAlex - Early Childhood · 6 Oct 2026