Exploratory decision trees to predict obesity intervention response among Hispanic-American youth

Authors: ARLINGHAUS, KATHERINE - University Of Minnesota; O'CONNOR, DANIEL - University Of Houston; LEDOUX, TRACEY - University Of Houston; HUGHES, SHERYL - Children'S Nutrition Research Center (CNRC); JOHNSTON, CRAIG - University Of Houston

Submitted to: Childhood Obesity
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/6/2022
Publication Date: 6/13/2022
Citation: Arlinghaus, K.R., O'Connor, D.P., Ledoux, T.A., Hughes, S.O., Johnston, C.A. 2022. Exploratory decision trees to predict obesity intervention response among Hispanic-American youth. Childhood Obesity. https://doi.org/10.1089/chi.2021.0296.
DOI: https://doi.org/10.1089/chi.2021.0296

Interpretive Summary: There exist individual differences in the way the weight status of youth changes in response to intervention. Given that this presents one of the greatest challenges to obesity prevention and treatment, researchers are only beginning to examine it. In clinical settings where treatment is administered at the individual level, treatment is modified or escalated when an individual is not responding well. In school-based interventions, in which an intervention is provided at a group level, those who do not respond as well (i.e., do not have improvements in weight outcomes) are often overlooked. Identifying these individuals who are unresponsive to school-based or other public health interventions and modifying their approach may improve the overall intervention impact, especially in marginalized communities who often face greater barriers. Additionally, understanding the characteristics that separate individuals who are responsive to an intervention from those who are not helps in tailoring the approach and prioritizing the resources appropriately. To address these gaps, this study used statistical methods to identify profiles of demographic characteristics, health indicators, and behavioral characteristics (e.g., sex, age, baseline weight, physical activity, dietary consumption, health-related quality of life) that differentiated those who responded or did not respond to physical activity programming at 3 and 6 months, categorized by baseline weight status. The study was conducted with 185 low-income, Hispanic American middle school students who received a school-based obesity intervention. Overall, results revealed six distinct profiles for each weight status group and time point (3 and 6 months). While the profiles had some commonalities, the uniqueness of each profile shows the complex, variable nature of individual response to intervention. The results offer some direction for future research by identifying profiles of factors that cross to differentiate between those who make improvements in weight-related outcomes and those who do not. This study highlights the importance of early identification of youth who do not respond as well initially to an intervention because they are also unlikely to respond later. The current study is one of the first to document this among a school-based intervention.

Technical Abstract: Individual variability in weight-related outcomes from obesity intervention is widely acknowledged, yet infrequently addressed. This study takes a first step to address individual variation by determining characteristics that distinguish responsive (improvements in BMI) from unresponsive individuals. Classification regression tree (CRT) analysis grouped 185 low-income, Hispanic American middle school students who received a school-based obesity intervention. Predictors included baseline age, gender, standardized BMI, health-related quality of life (PedsQL), minutes of moderate-vigorous physical activity (MVPA; accelerometry), energy consumption, and dietary quality (Block Kids 2004 Food Frequency Questionnaire). Response regarding weight-related outcomes to the intervention was defined according to the American Academy of Pediatrics (AAP) guidelines. Six trees were produced, one for 3- and one for 6-month outcomes among all participants, participants with healthy weight status, and participants with overweight/obesity at baseline. The AAP criteria for response were met by 57.3% and 35.1% of participants at 3 and 6 months, respectively. CRT produced six unique trees. Notably, minutes of MVPA appeared twice (the first time at the top of the tree) in most 3-month models. In addition, response at 3 months consistently appeared as the first variable in all the 6-month models. Overall, the number of distinct pathways and the repeated appearance of the same variable within a pathway illustrate the complex, interactive nature of factors predicting an intervention response. Initially unresponsive individuals were unlikely to respond later in the intervention. More complex modeling is needed to better understand how to best predict who will be responsive to interventions.