Impact of Exposure Uncertainty on the Association between Perfluorooctanoate and Preeclampsia in the C8 Health Project Population

BACKGROUND: Uncertainty in exposure estimates from models can result in exposure measurement error and can potentially affect the validity of epidemiological studies. We recently used a suite of environmental models and an integrated exposure and pharmacokinetic model to estimate individual perfluorooctanoate (PFOA) serum concentrations and assess the association with preeclampsia from 1990 through 2006 for the C8 Health Project participants. OBJECTIVES: The aims of the current study are to evaluate impact of uncertainty in estimated PFOA drinking-water concentrations on estimated serum concentrations and their reported epidemiological association with preeclampsia. METHODS: For each individual public water district, we used Monte Carlo simulations to vary the year-by-year PFOA drinking-water concentration by randomly sampling from lognormal distributions for random error in the yearly public water district PFOA concentrations, systematic error specific to each water district, and global systematic error in the release assessment (using the estimated concentrations from the original fate and transport model as medians and a range of 2-, 5-, and 10-fold uncertainty). RESULTS: Uncertainty in PFOA water concentrations could cause major changes in estimated serum PFOA concentrations among participants. However, there is relatively little impact on the resulting epidemiological association in our simulations. The contribution of exposure uncertainty to the total uncertainty (including regression parameter variance) ranged from 5% to 31%, and bias was negligible. CONCLUSIONS: We found that correlated exposure uncertainty can substantially change estimated PFOA serum concentrations, but results in only minor impacts on the epidemiological association between PFOA and preeclampsia.