Exposure to environmental chemicals has been shown to affect health status throughout the life course. Quantifying the joint effect of environmental mixtures over time is crucial to determine optimal intervention timing. Establishing causal relationships from environmental mixture data can be challenging due to various factors, including multicollinearity, complex functional form of exposure-response relationships, and residual unmeasured confounding. These issues can lead to biased estimates of treatment effects and pose significant obstacles in accurately identifying the true relationship between the pollutants and outcome variables. Causal interpretation of longitudinal environmental mixture studies encounters challenges.
This dissertation explores the use of causal inference in environmental mixture studies, with a particular emphasis on addressing three key challenges. First, there is currently no statistical approach that allows simultaneous consideration of time-varying confounding, flexible modeling, and variable selection when examining the effect of multiple, correlated, and time-varying exposures. Second, the violation of a critical assumption that underpins all causal inference methods - namely, the absence of unmeasured confounding - poses a significant problem, as models that incorporate multiple environmental exposures may exacerbate the degree of bias depending on the nature of unmeasured confounding. Finally, there is a lack of computational resources that facilitate the application of newly developed causal inference methods for analyzing environmental mixtures.
In Chapter 2, we introduce a causal inference method, g-BKMR, which enables to estimate nonlinear, non-additive effects of time-varying exposures and time-varying confounders, while also allowing for variable selection. An extensive simulation study shows that g-BKMR outperforms approaches that rely on correct model specification or do not account for time-dependent confounding, especially when correlation across time-varying exposures is high or the exposure-outcome relationship is nonlinear. We apply g-BKMR to quantify the contribution of metal mixtures to blood glucose in the Strong Heart Study, a prospective cohort study of American Indians.
Chapter 3, we address the issue of time-varying unmeasured confounding when estimating time-varying effects of exposure to environmental chemicals. We review the Bayesian g-formula under the assumption of no unmeasured confounding, and then introduce a Bayesian probabilistic sensitivity analysis approach that can account for multiple, potentially time-varying, unmeasured confounders and continuous exposures. Through a simulation study, we demonstrate that the proposed algorithm outperforms the naive method, which fails to consider the influence of confounding.
Chapter 4, introduces causalbkmr, a novel R package and can be currently be accessed on Github. causalbkmr is designed to support the implementation of g-BKMR, BKMR Causal Mediation Analysis, and Multiple Imputation BKMR, thereby offering a user-friendly and effective platform for executing these state-of-the-art methods in practice in the context of complex mixtures analysis. While the package bkmr is available, the novel package causalbkmr expands upon bkmr by enabling its application specifically to environmental mixture data within a causal inference framework. The implementation of these novel methodologies within causalbkmr allows for the extraction of causal interpretations, thus enhancing the analytical capabilities provided by the package.
Chapter 5 concludes with a discussion and outlines potential future directions for investigation.
| Identifer | oai:union.ndltd.org:columbia.edu/oai:academiccommons.columbia.edu:10.7916/16fh-nh59 |
| Date | January 2023 |
| Creators | Chai, Zilan |
| Source Sets | Columbia University |
| Language | English |
| Detected Language | English |
| Type | Theses |
Page generated in 0.0022 seconds