Upstream adverse effects in risk assessment: A model of polychlorinated biphenyls, thyroid hormone disruption and neurological outcomes in humans

Abstract

BackgroundIncreasing data on early biological changes from chemical exposures requires new interpretation tools to support decision-making. ObjectivesTo test the possibility of applying a quantitative approach using human data linking chemical exposures and upstream biological perturbations to overt downstream outcomes. MethodsUsing polychlorinated biphenyl (PCB) exposures and maternal thyroid hormone (TH) perturbations as a case study, we model three relationships: (1) prenatal PCB exposures and TH changes, using free T4 (FT4); (2) prenatal TH and childhood neurodevelopmental outcomes; and (3) prenatal PCB exposures and childhood neurodevelopmental outcomes (IQ). We surveyed the epidemiological literature; extracted relevant quantitative data; and developed models for each relationship, applying meta-analysis where appropriate. ResultsFor relationship 1, a meta-analysis of 3 studies gives a coefficient of −0.27pg/mL FT4 per ln(sum of PCBs) (95% confidence interval [CI] −0.82 to 0.27). For relationship 2, regression coefficients from three studies of maternal FT4 levels and cognitive scores ranged between 0.99 IQ points/(pg/mL FT4) (95% CI −0.31 to 2.2) and 7.6 points/(pg/mL FT4) (95% CI 1.2 to 16.3). For relationship 3, a meta-analysis of five studies produces a coefficient of −1.98 IQ points (95% CI −4.46 to 0.50) per unit increase in ln(sum of PCBs). Combining relationships 1 and 2 yields an estimate of −2.0 to −0.27 points of IQ per unit increase in ln(sum of PCBs). ConclusionsCombining analysis of chemical exposures and early biological perturbations (PCBs and FT4) with analysis of early biological perturbations and downstream overt effects (FT4 and IQ) yields estimates within the range of studies of exposures and overt effects (PCBs and IQ). This is an example approach using upstream biological perturbations for effect prediction.