Prenatal Arsenic Exposure and Birth Outcomes among a Population Residing near a Mining-Related Superfund Site

Abstract

Background: Limited epidemiologic data exist on prenatal arsenic exposure and fetal growth, particularly in the context of co-exposure to other toxic metals.

Objective: We examined whether prenatal arsenic exposure predicts birth outcomes among a rural U.S. population, while adjusting for exposure to lead and manganese.

Methods: We collected maternal and umbilical cord blood samples at delivery from 622 mother-infant pairs residing near a mining-related Superfund site in Northeast Oklahoma. Whole blood arsenic, lead, and manganese were measured using inductively coupled plasma mass spectrometry. We modeled associations between arsenic concentrations and birth weight, gestational age, head circumference, and birth weight for gestational age.

Results: Median (25th-75th percentile) maternal and umbilical cord blood metal concentrations, respectively, were as follows: arsenic, 1.4 (1.0-2.3) and 2.4 (1.8-3.3) μg/L; lead, 0.6 (0.4-0.9) and 0.4 (0.3-0.6) μg/dL; manganese, 22.7 (18.8-29.3) and 41.7 (32.2-50.4) μg/L. We estimated negative associations between maternal blood arsenic concentrations and birth outcomes. In multivariable regression models adjusted for lead and manganese, an interquartile range increase in maternal blood arsenic was associated with -77.5 g (95% CI: -127.8, -27.3) birth weight, -0.13 weeks (95% CI: -0.27, 0.01) gestation, -0.22 cm (95% CI: -0.42, -0.03) head circumference, and -0.14 (95% CI: -0.24, -0.04) birth weight for gestational age z-score units. Interactions between arsenic concentrations and lead or manganese were not statistically significant.

Conclusions: In a population with environmental exposure levels similar to the U.S. general population, maternal blood arsenic was negatively associated with fetal growth. Given the potential for relatively common fetal and early childhood arsenic exposures, our finding that prenatal arsenic can adversely affect birth outcomes is of considerable public health importance.

Citation: Claus Henn B, Ettinger AS, Hopkins MR, Jim R, Amarasiriwardena C, Christiani DC, Coull BA, Bellinger DC, Wright RO. 2016. Prenatal arsenic exposure and birth outcomes among a population residing near a mining-related Superfund site. Environ Health Perspect 124:1308-1315; http://dx.doi.org/10.1289/ehp.1510070.

Figure 1

Effect estimates and 95% confidence intervals for quartiles of maternal blood arsenic with birth weight (BW), gestational age (GA), weight for gestational age (BW for GA), and head circumference (HC). Generalized additive models include maternal blood lead and manganese (smoothed), maternal age at delivery (smoothed), infant sex, race/ethnicity, parity, smoking during pregnancy, maternal education, prenatal vitamin use, and maternal hemoglobin at delivery (n = 596 for BW, GA, BW for GA; n = 574 for HC). Dashed horizontal line represents null association.

Figure 2

Effect estimates and 95% confidence intervals for quartiles of cord blood arsenic with birth weight (BW), gestational age (GA), weight for gestational age (BW for GA), and head circumference (HC). Generalized additive models include cord blood lead and manganese (smoothed), maternal age at delivery (smoothed), infant sex, race/ethnicity, parity, smoking during pregnancy, maternal education, prenatal vitamin use, and maternal hemoglobin at delivery (n = 588 for BW, GA, BW for GA; n = 565 for HC). Dashed horizontal line represents null association.