Causal evaluation of the health effects of light rail line: A natural experiment

Abstract

Background and objectiveNo research to date has causally linked built environment data with health care costs derived from clinically assessed health outcomes within the framework of longitudinal intervention design. This study examined the impact of light rail transit (LRT) line intervention on health care costs after controlling for mode-specific objectively assessed moderate-to-vigorous physical activity (MVPA), participant-level neighborhood environmental measures, demographics, attitudinal predispositions, and residential choices. Data and methodsBased on a natural experiment related to a new LRT line in Portland – 282 individuals divided into treatment and control groups were prospectively followed during the pre- and post-intervention periods. For each individual, we harness high-resolution data on Electronic Medical Record (EMR) based health care costs, mode-specific MVPA, survey-based travel behavior, attitudinal/perception information, and objectively assessed built environment measures. Simulation-assisted longitudinal grouped random parameter models are developed to gain more accurate insights into the effects of LRT line intervention. ResultsRegarding the “average effect” of the LRT line intervention, no statistically significant reductions in health care costs were observed for the treated individuals over time. However, substantial heterogeneity was observed not only in the magnitude of effects but its direction as well after controlling for the within- and between-individual variations. For a subgroup of treated individuals, the LRT line opening decreased health care costs over time relative to the control group. Further comparative analysis based on the findings of heterogeneity-based models revealed that the effect of LRT intervention for the treated individuals differed by individual characteristics, attitudes/perceptions, and neighborhood level environmental features. ConclusionsThe study revealed the presence of significant effect modifiers and distinct subgroup structures in the data related to the effects of LRT line intervention on health care costs. Severe implications of ignoring unobserved heterogeneity are highlighted. Limitations and potential avenues for future research are discussed.