Executive and Reward-Related Function in Pediatric Obesity: A Meta-Analysis

Abstract

Objective: This study examined the effect of pediatric obesity on executive function and reward-related decision-making, cognitive processes that are relevant to obesogenic behaviors, and evaluated their association with sample (e.g., age, gender, intelligence, and socioeconomic status, SES) and study/task (e.g., categorical/continuous variable, food stimuli) characteristics.

Methods: A random-effects meta-analysis was conducted using Hedge's g effect sizes of published studies from 1960 to 2016, limited to children younger than the age of 21 years without medical comorbidities. Analysis included estimation of heterogeneity (τ²), publication bias (funnel-plot symmetry and fail-safe N), and sensitivity analyses for sample and study/task characteristics.

Results: Across 68 studies with 70 samples, obesity was associated with worse functioning overall (-0.24; 95CI: -0.30 to -0.19; p < 0.001) and for each component process (attention, switching, inhibition, interference, working memory, reward, delay of gratification: -0.19 to -0.38; p's < 0.017), except trait impulsivity (-0.06; 95CI: -0.18 to 0.07). Deficits increased with age and female composition of the sample for inhibition (p = 0.002). No other characteristics moderated effect of obesity.

Conclusions: Small-to-moderate negative associations with obesity were observed for executive and reward-related performance, but not on reported impulsivity in studies with children younger than the age of 21 years. These results were not moderated by IQ, SES, and study/task characteristics. Age and gender moderated association with inhibition, with a larger obesity-related deficit in older and predominantly female samples. These results suggest cognitive and demographic intervention targets for prevention and mitigation of obesogenic behavior.

Keywords: IQ; SES; attention; executive function; reward.

FIG. 1.

Flowchart depicting results and method the systematic review.

FIG. 2.

These plots depict significant moderators of the effect of obesity on executive abilities with the moderator Age shown in A and B, sample composition in C, Task Type in D, and Study Design in E. The size of the points on the graphs relate to the contribution or weight of that study in the model. The dotted lines reflect predicted marginal effects with 95% confidence intervals.