Assessment of Grouped Weighted Quantile Sum Regression for Modeling Chemical Mixtures and Cancer Risk

Abstract

Individuals are exposed to a large number of diverse environmental chemicals simultaneously and the evaluation of multiple chemical exposures is important for identifying cancer risk factors. The measurement of a large number of chemicals (the exposome) in epidemiologic studies is allowing for a more comprehensive assessment of cancer risk factors than was done in earlier studies that focused on only a few chemicals. Empirical evidence from epidemiologic studies shows that chemicals from different chemical classes have different magnitudes and directions of association with cancers. Given increasing data availability, there is a need for the development and assessment of statistical methods to model environmental cancer risk that considers a large number of diverse chemicals with different effects for different chemical classes. The method of grouped weighted quantile sum (GWQS) regression allows for multiple groups of chemicals to be considered in the model such that different magnitudes and directions of associations are possible for each group of chemicals. In this paper, we assessed the ability of GWQS regression to estimate exposure effects for multiple chemical groups and correctly identify important chemicals in each group using a simulation study. We compared the performance of GWQS regression with WQS regression, the least absolute shrinkage and selection operator (lasso), and the group lasso in estimating exposure effects and identifying important chemicals. The simulation study results demonstrate that GWQS is an effective method for modeling exposure to multiple groups of chemicals and compares favorably with other methods used in mixture analysis. As an application, we used GWQS regression in the California Childhood Leukemia Study (CCLS), a population-based case-control study of childhood leukemia in California to estimate exposure effects for many chemical classes while also adjusting for demographic factors. The CCLS analysis found evidence of a positive association between exposure to the herbicide dacthal and an increased risk of childhood leukemia.

Imputation of Below Detection Limit Missing Data in Chemical Mixture Analysis with Bayesian Group Index Regression

“…Single-chemical logistic regression analyses have also found significant positive associations between leukemia and PCB138 as well as between leukemia and summed total PCB concentrations [56]. Similarly, the significant positive association found for herbicides (and the dominance of dacthal within the index) closely mirrors prior analyses of these data done using Bayesian group index regression analysis with a different imputation approach [23] and GWQS regression [24]. Besides these mixture analyses, univariable logistic regression analyses have found similar associations between dacthal and childhood acute lymphocytic leukemia (ALL) risk [57].…”

“…The association of PCBs with leukemia reflects the findings of earlier work. In a previous study of the CCLS cohort, group index regression methods found a marginally significant association between PCBs and childhood leukemia, with PCB 138 contributing the most to the index effect [24]. Single-chemical logistic regression analyses have also found significant positive associations between leukemia and PCB138 as well as between leukemia and summed total PCB concentrations [56].…”

“…We first fit the 7-group exposure model and then evaluated high family income as a potential effect modifier because it was a consistently significant covariate in previous analyses [23,24].To investigate potential effect moderation, we extended the 7-group model to include seven interaction terms between each index and the highest income level. We then conducted a stratified analysis and dichotomized into the highest income bracket ($75,000+) as one level and the lower five brackets ($0-$74,999) as the second.…”

“…More recently, group index models were developed to allow for multiple chemical groups, where each of the groups can have different magnitudes and direction of association with the outcome [20,21]. There are both frequentist and Bayesian versions of group index models, with Bayesian models being able to estimate all model parameters simultaneously in one step [21][22][23][24].…”

Quantifying the Effect Size of Exposure-Outcome Association Using δ-score: Application to Environmental Chemical Mixture studies

“…There has been a welcome surge of interest in estimating health effects of exposure-mixture in environmental epidemiology (Bobb et al (2014), Carrico et al (2015), Colicino et al (2020), Keil et al (2020), Wheeler et al (2021), Ferrari and Dunson (2021)). These developments are certainly promising but most of these methods use traditional null hypothesis significance testing (NHST) for exposure mixture-outcome associations.…”