Longitudinal associations of neighbourhood environmental exposures with mental health problems during adolescence: Findings from the TRAILS study

Background: Cross-sectional studies have found associations between neighbourhood environments and adolescent mental health, but the few longitudinal studies mainly focused on single exposure-based analyses and rarely assessed the mental health associations with environmental changes. Objectives: We assessed longitudinal within- and between-person associations of multiple neighbourhood time-varying physical and social environmental exposures with externalising and internalising problems throughout adolescence. Methods: We used four waves of TRAILS (Tracking Adolescents' Individual Lives Survey) data on self-reported externalising and internalising problems at ages 11, 13, 16, and 19 among 2,135 adolescents in the Netherlands. We measured residence-based time-varying environmental exposures, including green space, air pollution (fine particulate matter (PM2.5)), noise, deprivation, and social fragmentation. We fitted random-effect within-between regression models to assess the environment-mental health associations. Results: At the within-person level, an interquartile range (IQR) increase in PM2.5 was associated with a 0.056 IQR (95% CI: 0.014, 0.099) increase in externalising problems, while an IQR social fragmentation increase was associated with a 0.010 IQR (95% CI: -0.020, -0.001) decrease in externalising problems. Stratification revealed that the association with PM2.5 was significant only for movers, whereas the association with social fragmentation remained only for non-movers. At the between-person level, an IQR higher noise was associated with a 0.100 IQR (95% CI: 0.031, 0.169) more externalising problems, while higher deprivation (beta = 0.080; 95% CI: 0.022, 0.138) and lower fragmentation (beta = -0.073; 95% CI: -0.128, -0.018) were associated with more internalising problems. We also observed positive between-person associations between PM2.5, noise, and internalising problems, but both associations were unstable due to the high PM2.5-noise correlation. Further, we observed a non-linear between-person PM2.5-externalising problems association turning positive when PM2.5 > 15 mu g/m(3). Null associations were found for green space. Conclusion: Our findings suggested that air pollution, noise, and neighbourhood deprivation are risk factors for adolescent mental health. Not only exposure levels but also exposure changes matter for adolescent mental health.