“Heterogeneous treatment effects” is a term which refers to conditional average treatment effects (i.e., CATEs) that vary across population subgroups. Epidemiologists are often interested in estimating such effects because they can help detect populations who may particularly benefit from or be harmed by a treatment. However, standard regression approaches for estimating heterogeneous effects are limited by pre-existing hypotheses, test a single effect modifier at a time, and are subject to the multiple comparisons problem. The objective of this text is to offer a practical guide to honest causal forests, an ensemble tree-based learning method which can discover as well as estimate heterogeneous treatment effects using a data-driven approach. We discuss the fundamentals of tree-based methods, describe how honest causal forests can identify and estimate heterogeneous effects, and demonstrate an implementation of this method using simulated data. Our implementation highlights the steps required to simulate datasets, build honest causal forests, and assess model performance across a variety of simulation scenarios. Overall, this paper is intended for epidemiologists and other population health researchers who lack an extensive background in machine learning yet are interested in utilizing an emerging method for identifying and estimating heterogeneous treatment effects.

Racial residential segregation is associated with multiple adverse health outcomes in Black individuals. Yet, the influence of structural racism and racial residential segregation on brain aging is less understood. In this study, we investigate the association between cumulative exposure to racial residential segregation over 25 years (1985-2010) of young adulthood, measured by the Getis-Ord Gi*-statistic, and year 25 measures of brain volume in midlife (cerebral, gray matter, white matter, and hippocampal volumes). We studied 290 Black participants with available brain imaging data who were enrolled in the Coronary Artery Risk Development in Young Adults (CARDIA) prospective cohort study. CARDIA originally recruited 2637 Black participants aged 18 to 30 years old from 4 field centers across the United States. We conducted analyses using marginal structural models, incorporating inverse probability weighting and inverse censoring weighting. We found that compared to low/medium segregation, greater cumulative exposure to residential segregation throughout young adulthood was associated with smaller brain volumes in general (e.g. β for cerebral volume: -0.08 [95% CI]: [-0.15, -0.02]) and with a more pronounced reduction in hippocampal volume, though results were not statistically significant. Our findings suggest that exposure to segregated neighborhoods may be associated with worse brain aging.

Background Despite their well-established benefits for the prevention of cardiovascular disease, robust evidence on the effects of statins on cognition is largely inconclusive. We apply various study designs and analytical approaches to mimic randomized controlled trial (RCT) effects from observational data. Methods We used observational data from 5,580 participants enrolled in the Cardiovascular Health Study from 1989/90 to 1999/2000. We conceptualized the cohort as an overlapping sequence of non-randomized trials. We compared multiple selection (eligible population, prevalent users, new-users) and analytic approaches (multivariable adjustment, inverse probability treatment weights, propensity score matching) to evaluate the association between statin use and 5-year change in global cognitive function, assessed using the Modified Mini-Mental State (3MS) examination. Results When comparing prevalent users to non-users (N=2,772), statin use was associated with slower cognitive decline over 5 years (adjusted annual change in 3MSE = 0.34 points/year; 95% CI:0.05;0.63). Compared to prevalent user design, estimates from new user designs (e.g. comparing eligible statin initiators to non-initiators) were attenuated showing either null or negative association, though not significant. For example, in a propensity score-matched sample of statin-eligible individuals (N=454), annual 3MS change comparing statin initiators to non-initiators was -0.21 points/year (95% CI:-0.81;0.39). Conclusions The association of statin use and cognitive decline is attenuated towards the null when using rigorous analytical approaches that more closely mimic RCTs. Point estimates, even within the same study, may vary depending on the analytical methods used. Further studies that leverage natural or quasi experiments around statin use are needed to replicate our findings.

ImportanceFood insecurity is a leading public health issue in the US. Research on food insecurity and cognitive aging is scarce, and is mostly cross-sectional. Food insecurity status and cognition both can change over the life course, but their longitudinal relationship remains unexplored.ObjectiveTo examine the longitudinal association between food insecurity and changes in memory function during a period of 18 years among middle to older–aged adults in the US.Design, Setting, and ParticipantsThe Health and Retirement Study is an ongoing population-based cohort study of individuals aged 50 years or older. Participants with nonmissing information on their food insecurity in 1998 who contributed information on memory function at least once over the study period (1998-2016) were included. To account for time-varying confounding and censoring, marginal structural models were created, using inverse probability weighting. Data analyses were conducted between May 9 and November 30, 2022.Main outcomes and MeasuresIn each biennial interview, food insecurity status (yes/no) was assessed by asking respondents whether they had enough money to buy food or ate less than they felt they should. Memory function was a composite score based on self-completed immediate and delayed word recall task of a 10-word list and proxy-assessed validated instruments.ResultsThe analytic sample included 12 609 respondents (mean [SD] age, 67.7 [11.0] years, 8146 [64.60%] women, 10 277 [81.51%] non-Hispanic White), including 11 951 food-secure and 658 food-insecure individuals in 1998. Over time, the memory function of the food-secure respondents decreased by 0.045 SD units annually (β for time, −0.045; 95% CI, −0.046 to −0.045 SD units). The memory decline rate was faster among food-insecure respondents than food-secure respondents, although the magnitude of the coefficient was small (β for food insecurity × time, −0.0030; 95% CI, −0.0062 to −0.00018 SD units), which translates to an estimated 0.67 additional (ie, excess) years of memory aging over a 10-year period for food-insecure respondents compared with food-secure respondents.Conclusions and RelevanceIn this cohort study of middle to older–aged individuals, food insecurity was associated with slightly faster memory decline, suggesting possible long-term negative cognitive function outcomes associated with exposure to food insecurity in older age.

Background Little is known about long-term lipid variability in young adulthood in relation to cognitive function and brain integrity in midlife. Methods We studied 3,328 adults from the Coronary Artery Risk Development in Young Adults. We defined low- and high- density lipoprotein (LDL, HDL) variability as the intra-individual standard deviation of lipid measurements over 20 years of young adulthood (1985–2005). Cognitive tests were administered in 2010. Brain scans were performed in 2010 on 714 participants. To facilitate comparison, cognitive tests and brain metrics were z-scored. Results Mean age at baseline was 25.4 years. Higher 20-year LDL variability was associated with worse verbal memory in midlife (β=-0.25, 95% CI [-0.42, -0.08]), adjusted for important covariates. Higher 20-year HDL variability was associated with worse processing speed in midlife (β=-0.80, 95% CI [-1.18, -0.41]) and brain integrity, e.g. smaller total brain volume (β=-0.58, 95% CI [-0.82, -0.34]) and worse total brain fractional anisotropy (β=-1.13, 95% CI [-1.87, -0.39]). Conclusions Higher long-term lipid variability in adulthood was associated with worse cognition and brain integrity in midlife, in a relatively young cohort.