Powering Research through Innovative Methods for Mixtures in Epidemiology (PRIME) Program: Novel and Expanded Statistical Methods

Abstract

Humans are exposed to a diverse mixture of chemical and non-chemical exposures across their lifetimes. Well-designed epidemiology studies as well as sophisticated exposure science and related technologies enable the investigation of the health impacts of mixtures. While existing statistical methods can address the most basic questions related to the association between environmental mixtures and health endpoints, there were gaps in our ability to learn from mixtures data in several common epidemiologic scenarios, including high correlation among health and exposure measures in space and/or time, the presence of missing observations, the violation of important modeling assumptions, and the presence of computational challenges incurred by current implementations. To address these and other challenges, NIEHS initiated the Powering Research through Innovative methods for Mixtures in Epidemiology (PRIME) program, to support work on the development and expansion of statistical methods for mixtures. Six independent projects supported by PRIME have been highly productive but their methods have not yet been described collectively in a way that would inform application. We review 37 new methods from PRIME projects and summarize the work across previously published research questions, to inform methods selection and increase awareness of these new methods. We highlight important statistical advancements considering data science strategies, exposure-response estimation, timing of exposures, epidemiological methods, the incorporation of toxicity/chemical information, spatiotemporal data, risk assessment, and model performance, efficiency, and interpretation. Importantly, we link to software to encourage application and testing on other datasets. This review can enable more informed analyses of environmental mixtures. We stress training for early career scientists as well as innovation in statistical methodology as an ongoing need. Ultimately, we direct efforts to the common goal of reducing harmful exposures to improve public health.

Exposure to Metal Mixtures in Association with Cardiovascular Risk Factors and Outcomes: A Scoping Review

“…Given these findings, and the potentially complicated interactions between metal and non-metal exposures, future studies may also consider other relevant chemical or non-chemical exposures within their mixtures. New analysis methods which are both reproducible and efficient are also greatly needed to accommodate the growing body of biomedical data, including high-dimensional exposome data [ 23 ].…”

“…For example, Zn—an essential metal—can alleviate Cd’s pathogenic impacts [ 94 , 95 ]. Recent advancements in mixture analysis methods have enabled estimating and testing interactions among exposures in their effects on outcomes [ 23 ].…”

“…Given the potential cardiotoxicity of metal exposures, understanding the role of metal mixture exposures in the development of CVDs is of public health importance. Recognizing the importance of studying complex mixtures of environmental chemicals and their effects on human health, the NIEHS has developed the Combined Exposure and Mixtures Working Group [ 97 ] and the PRIME program [ 23 , 31 ]. This increased focus and dedication of resources has helped the field of environmental epidemiology unravel the more complete mechanisms underlying the cardiotoxicity of metal mixtures [ 97 ].…”

“…Recognizing that most individuals are exposed to complex mixtures of chemicals, the National Institute of Environmental Health Sciences (NIEHS) has encouraged the field to move towards systematically addressing the impacts of combined exposures, since its first dedicated funding mechanism for studying mixtures in 1998 [ 20 ]. More recently, the NIEHS has held several mixtures workshops and developed the Powering Research through Innovative Methods for Mixtures in Epidemiology (PRIME) Program to enhance understanding of complex exposures, prioritize mixture research goals, and recommend research collaborations across multidisciplinary settings [ 21 , 22 , 23 ]. As a result, several novel statistical methods have been developed for evaluating the effects of environmental chemical mixtures on health outcomes, including Bayesian kernel machine regression (BKMR) [ 24 ], weighted quantile sum regression (WQSR) [ 25 ], and quantile-based g-computation [ 26 ].…”

Integrating Biological Knowledge in Kernel-Based Analyses of Environmental Mixtures and Health

“…In recent years, methods for analyzing environmental mixtures have proliferated, with proposed methods including: linear index models (Carrico and others, 2015;Keil and others, 2020), single and multiple index models (Wang and others, 2020;McGee and others, 2021), exposure-response surface methods others, 2015, 2018;Vieira and others, 2021), shrinkage and selection priors (Dunson and others, 2008a;Herring, 2010;Antonelli and others, 2020), dimension reduction approaches like profile regression (Molitor and others, 2010(Molitor and others, , 2011(Molitor and others, , 2014 and Dirichlet process mixture models others, 2008b, 2007), among others (for recent reviews, see Davalos and others, 2017;Hamra and Buckley, 2018;Tanner and others, 2020;Joubert and others, 2022). Despite these statistical advances, most existing approaches do not make use of available knowledge about the toxicity of mixture components from the toxicological sciences.…”