A0210
Title: Statistical tools for assessing mixtures effects on health outcomes: A trade-off between complexity and interpretability
Authors: Susana Diaz Coto - Geisel School of Medicine at Dartmouth. Dartmouth Health (United States) [presenting]
Abstract: Several studies have explored the joint effect of mixtures of metals on health outcomes by using sophisticated statistical techniques, such as Bayesian kernel machine regression (BKMR). Although this method can detect complex relationships between metals, final conclusions are usually simplified in terms of an increase/decrease of the risk function at fixed values for individual metals. The feasibility and interpretability of BKMR are analytically and graphically explored to assess the effect of metal mixture exposures on neuropsychological development in early childhood. The scores derived by the BKMR exposure-response function were computed and compared with those provided by traditional linear regression models (LRM). Pearson correlation coefficients of the estimations obtained by BKMR and LRM accounting for pairwise interactions between metals ranged from 0.92 to 0.95, for the three previously identified latent domains: Executive functions, motor functions, and visual and verbal functions. The observed differences between both estimations mainly occurred in participants having the lowest or highest values of individual metals, which suggests linearity in the associations and not high-order interactions. It is concluded that, in this case, employing linear regression to model the impact of mixtures on targeted outcomes led to similar results to more complex techniques, allowing a better understanding of both individual and interaction effects between metals.
