Prenatal Organophosphorus Pesticide Exposure and Child Neurodevelopment at 24 Months: An Analysis of Four Birth Cohorts

Abstract

Background: Organophosphorus pesticides (OPs) are used in agriculture worldwide. Residential use was common in the United States before 2001.

Objectives: We conducted a pooled analysis of four birth cohorts (children's centers; n = 936) to evaluate associations of prenatal exposure to OPs with child development at 24 months.

Methods: Using general linear models, we computed site-specific and pooled estimates of the association of total dialkyl (ΣDAP), diethyl (ΣDEP), and dimethylphosphate (ΣDMP) metabolite concentrations in maternal prenatal urine with mental and psychomotor development indices (MDI/PDI) and evaluated heterogeneity by children's center, race/ethnicity, and PON1 genotype.

Results: There was significant heterogeneity in the center-specific estimates of association for ΣDAP and ΣDMP and the MDI (p = 0.09, and p = 0.05, respectively), as well as heterogeneity in the race/ethnicity-specific estimates for ΣDAP (p = 0.06) and ΣDMP (p = 0.02) and the MDI. Strong MDI associations in the CHAMACOS population per 10-fold increase in ΣDAP (β = -4.17; 95% CI: -7.00, -1.33) and ΣDMP (β = -3.64; 95% CI: -5.97, -1.32) were influential, as were associations among Hispanics (β per 10-fold increase in ΣDAP = -2.91; 95% CI: -4.71, -1.12). We generally found stronger negative associations of ΣDAP and ΣDEP with the 24-month MDI for carriers of the 192Q PON1 allele, particularly among blacks and Hispanics.

Conclusions: Data pooling was complicated by center-related differences in subject characteristics, eligibility, and changes in regulations governing residential use of OPs during the study periods. Pooled summary estimates of prenatal exposure to OPs and neurodevelopment should be interpreted with caution because of significant heterogeneity in associations by center, race/ethnicity, and PON1 genotype. Subgroups with unique exposure profiles or susceptibilities may be at higher risk for adverse neurodevelopment following prenatal exposure.

Citation: Engel SM, Bradman A, Wolff MS, Rauh VA, Harley KG, Yang JH, Hoepner LA, Barr DB, Yolton K, Vedar MG, Xu Y, Hornung RW, Wetmur JG, Chen J, Holland NT, Perera FP, Whyatt RM, Lanphear BP, Eskenazi B. 2016. Prenatal organophosphorus pesticide exposure and child neurodevelopment at 24 months: an analysis of four birth cohorts. Environ Health Perspect 124:822-830; http://dx.doi.org/10.1289/ehp.1409474.

Figure 1

Distributions of dialkylphosphate metabolite sums in individual cohorts. The 25th, 50th, and 75th percentiles by center are represented by the lower, middle, and upper bars in the central boxes. The arithmetic mean by center is marked by the open diamond. Outliers at the upper and lower end of the exposure distribution are indicated by circles. Whiskers indicate 95% CIs.

Figure 2

Restricted cubic splines for log₁₀ ∑DAP association with the 24-month MDI in the (A) CHAMACOS cohort, (B) HOME cohort, (C) Columbia cohort, (D) Mount Sinai cohort, and (E) pooled population. Splines demonstrate a roughly linearly declining relationship in the individual cohorts and the overall pooled population below approximately 2 nmol/g creatinine, which attenuates at higher concentrations. Although the HOME (B) and Columbia (C) cohorts appear to show a U-shape curve, the 95% CIs (dashed lines) demonstrate substantial imprecision around these estimates.