Environmental Phenols and Growth in Infancy: The Infant Feeding and Early Development Study

Abstract

Context: Higher mean and rapid increases in body mass index (BMI) during infancy are associated with subsequent obesity and may be influenced by exposure to endocrine-disrupting chemicals such as phenols.

Objective: In a prospective US-based cohort conducted 2010-2014, we investigated associations between environmental phenol exposures and BMI in 199 infants.

Methods: We measured 7 urinary phenols at ages 6-8 and 12 weeks and assessed BMI z-score at up to 12 study visits between birth and 36 weeks. We examined individual and joint associations of averaged early infancy phenols with level of BMI z-score using mean differences (β [95% CI]) and with BMI z-score trajectories using relative risk ratios (RR [95% CI]).

Results: Benzophenone-3, methyl and propyl paraben, and all phenols jointly were positively associated with higher mean BMI z-score (0.07 [-0.05, 0.18], 0.10 [-0.08, 0.27], 0.08 [-0.09, 0.25], 0.17 [-0.08, 0.43], respectively). Relative to a stable trajectory, benzophenone-3, 2,4-dichlorophenol, 2,5-dichlorophenol, and all phenols jointly were positively associated with risk of a rapid increase trajectory (1.46 [0.89, 2.39], 1.33 [0.88, 2.01], 1.66 [1.03, 2.68], 1.41 [0.71, 2.84], respectively).

Conclusion: Early phenol exposure was associated with a higher mean and rapid increase in BMI z-score across infancy, signaling potential long-term cardiometabolic consequences of exposure.

Keywords: body mass index; growth trajectories; infant; longitudinal studies; phenols.

Figure 1.

Infant BMI z-score by age at each study visit among the infant feeding and early development study sample (N = 199), 2010-2014. In girls and boys, study visits were scheduled at 2 and 4 weeks (±4 days); 6, 8, and 12 weeks (±10 days); 16, 20, 24, and 28 weeks (±14 days). In girls, 2 additional study visits were scheduled at 32 weeks (±14 days) and 36 weeks (±30 days). In June 2012, the study visit at 6 weeks was discontinued. Dashed y-axis reference lines were placed at a BMI z-score of −1.96, 0, and 1.96.

Figure 2.

Associations between level of BMI z-score and phenol concentrations in the infant feeding and early development study sample (N = 199), 2010-2014. Abbreviations: BPA, bisphenol A. Dashed x-axis reference lines represent the null. We estimated single chemical individual associations with linear mixed effects regression and multichemical (Mixture) joint associations with parametric generalized linear regression and participant-specific random effects in quantile g-computation. Model covariates included infant sex assigned at birth, infant diet, infant race, maternal education, maternal age, smoking during pregnancy, alcohol use during pregnancy, and gestational age at birth. Phenol concentrations were creatinine-standardized, averaged using the geometric mean from up to 2 repeated measures, and log-transformed for analyses.

Figure 3.

BMI Z-score trajectory groups in the infant feeding and early development study sample (N = 199), 2010-2014. Before running growth mixture models to identify trajectory groups, BMI z-scores were centered by subtracting participant-specific mean BMI z-scores. (A) Plot of observed and predicted centered BMI z-score trajectory groups. Observed values indicated with shapes and colors according to group with highest probability of assignment. Predicted group trajectory and 95% CIs indicated with lines and colors according to group with highest probability of assignment. (B) Spaghetti plots of observed BMI z-scores for each assigned trajectory group. Trajectories are labeled and colored according to trajectory group with the highest probability of assignment. Dashed y-axis reference lines were placed at a BMI z-score of −1.96, 0, and 1.96.

Figure 4.

Associations between centered BMI z-score trajectory groups and phenol concentrations and in the infant feeding and early development study sample (N = 199), 2010-2014. Abbreviations: BPA, bisphenol A. The reference group for analyses was the “stable” trajectory. Dashed x-axis reference lines represent the null. We estimated single chemical individual associations with multinomial logistic regression and multichemical (mixture) joint associations with log-binomial regression in quantile g-computation. Models adjusted for infant sex assigned at birth, infant diet, infant race, maternal education, maternal age, smoking during pregnancy, alcohol use during pregnancy, and gestational age at birth. Phenol concentrations were creatinine-standardized, averaged using the geometric mean from up to 2 repeated measures, and log-transformed for analyses.