Model choice for estimating the association between exposure to chemical mixtures and health outcomes: A simulation study

Statistical methods for chemical mixtures: a roadmap for practitioners

Quantitative characterization of the health impacts associated with exposure to chemical mixtures has received considerable attention in current environmental and epidemiological studies. With many existing statistical methods and emerging approaches, it is important for practitioners to understand when each method is best suited for their inferential goals. In this study, we conduct a review and comparison of 11 analytical methods available for use in mixtures research, through extensive simulation studies for continuous and binary outcomes. These methods fall in three different classes: identifying important components of a mixture, identifying interactions and creating a summary score for risk stratification and prediction. We carry out an illustrative data analysis in the PROTECT birth cohort from Puerto Rico. Most importantly we develop an integrated package "CompMix" that provides a platform for mixtures analysis where the practitioner can implement a pipeline for several types of mixtures analysis. Our simulation results suggest that the choice of methods depends on the goal of analysis and there is no clear winner across the board. For selection of important toxicants in the mixture and for identifying interactions, Elastic net by Zou et al. (Enet), Lasso for Hierarchical Interactions by Bien et al (HierNet), Selection of nonlinear interactions by a forward stepwise algorithm by Narisetty et al. (SNIF) have the most stable performance across simulation settings. Additionally, the predictive performance of the Super Learner ensembling method by Van de Laan et al. and HierNet are found to be superior to the rest of the methods. For overall summary or a cumulative measure, we find that using the Super Learner to combine multiple Environmental Risk Scores can lead to improved risk stratification properties. We have developed an R package "CompMix: A comprehensive toolkit for environmental mixtures analysis", allowing users to implement a variety of tasks under different settings and compare the findings. In summary, our study offers guidelines for selecting appropriate statistical methods for addressing specific scientific questions related to mixtures research. We identify critical gaps where new and better methods are needed.

Associations of urinary non-persistent endocrine disrupting chemical biomarkers with early-to-mid pregnancy plasma sex-steroid and thyroid hormones

BACKGROUND/OBJECTIVES

Pregnant women are exposed to numerous endocrine disrupting chemicals (EDCs) that can affect hormonal pathways regulating pregnancy outcomes and fetal development. Thus, we evaluated overall and fetal sex-specific associations of phthalate/replacement, paraben, and phenol biomarkers with sex-steroid and thyroid hormones.

METHODS

Illinois women (n = 302) provided plasma for progesterone, estradiol, testosterone, free T4 (FT4), total T4 (TT4), and thyroid stimulating hormone (TSH) at median 17 weeks gestation. Women also provided up-to-five first-morning urine samples monthly across pregnancy (8-40 weeks), which we pooled to measure 19 phthalate/replacement metabolites (reflecting ten parent compounds), three parabens, and six phenols. We used linear regression to evaluate overall and fetal sex-specific associations of biomarkers with hormones, as well as weighted quantile sum and Bayesian kernel machine regression (BKMR) to assess cumulative associations, non-linearities, and chemical interactions.

RESULTS

In women of relatively high socioeconomic status, several EDC biomarkers were associated with select hormones, without cumulative or non-linear associations with progesterone, FT4, or TT4. The biomarker mixture was negatively associated with estradiol (only at higher biomarker concentrations using BKMR), testosterone, and TSH, where each 10% mixture increase was associated with -5.65% (95% CI: -9.79, -1.28) lower testosterone and -0.09 μIU/mL (95% CI: -0.20, 0.00) lower TSH. Associations with progesterone, testosterone, and FT4 did not differ by fetal sex. However, in women carrying females, we identified an inverted u-shaped relationship of the mixture with estradiol. Additionally, in women carrying females, each 10% increase in the mixture was associated with 1.50% (95% CI: -0.15, 3.18) higher TT4, whereas in women carrying males, the mixture was associated with -1.77% (95% CI: -4.08, 0.58) lower TT4 and -0.18 μIU/mL (95% CI: -0.33, -0.03) lower TSH. We also identified select chemical interactions.

CONCLUSION

Some biomarkers were associated with early-to-mid pregnancy hormones. There were some sex-specific and non-linear associations. Future studies could consider how these findings relate to pregnancy/birth outcomes.

Methodological Challenges in Spatial and Contextual Exposome-Health Studies

The concept of the exposome encompasses the totality of exposures from a variety of external and internal sources across an individual's life course. The wealth of existing spatial and contextual data makes it appealing to characterize individuals' external exposome to advance our understanding of environmental determinants of health. However, the spatial and contextual exposome is very different from other exposome factors measured at the individual-level as spatial and contextual exposome data are more heterogenous with unique correlation structures and various spatiotemporal scales. These distinctive characteristics lead to multiple unique methodological challenges across different stages of a study. This article provides a review of the existing resources, methods, and tools in the new and developing field for spatial and contextual exposome-health studies focusing on four areas: (1) data engineering, (2) spatiotemporal data linkage, (3) statistical methods for exposome-health association studies, and (4) machine- and deep-learning methods to use spatial and contextual exposome data for disease prediction. A critical analysis of the methodological challenges involved in each of these areas is performed to identify knowledge gaps and address future research needs.

Using non-parametric Bayes shrinkage to assess relationships between multiple environmental and social stressors and neonatal size and body composition in the Healthy Start cohort

BACKGROUND

Both environmental and social factors have been linked to birth weight and adiposity at birth, but few studies consider the effects of exposure mixtures. Our objective was to identify which components of a mixture of neighborhood-level environmental and social exposures were driving associations with birth weight and adiposity at birth in the Healthy Start cohort.

METHODS

Exposures were assessed at the census tract level and included air pollution, built environment characteristics, and socioeconomic status. Prenatal exposures were assigned based on address at enrollment. Birth weight was measured at delivery and adiposity was measured using air displacement plethysmography within three days. We used non-parametric Bayes shrinkage (NPB) to identify exposures that were associated with our outcomes of interest. NPB models were compared to single-predictor linear regression. We also included generalized additive models (GAM) to assess nonlinear relationships. All regression models were adjusted for individual-level covariates, including maternal age, pre-pregnancy BMI, and smoking.

RESULTS

Results from NPB models showed most exposures were negatively associated with birth weight, though credible intervals were wide and generally contained zero. However, the NPB model identified an interaction between ozone and temperature on birth weight, and the GAM suggested potential non-linear relationships. For associations between ozone or temperature with birth weight, we observed effect modification by maternal race/ethnicity, where effects were stronger for mothers who identified as a race or ethnicity other than non-Hispanic White. No associations with adiposity at birth were observed.

CONCLUSIONS

NPB identified prenatal exposures to ozone and temperature as predictors of birth weight, and mothers who identify as a race or ethnicity other than non-Hispanic White might be disproportionately impacted. However, NPB models may have limited applicability when non-linear effects are present. Future work should consider a two-stage approach where NPB is used to reduce dimensionality and alternative approaches examine non-linear effects.