Association of Prenatal and Perinatal Exposures to Particulate Matter With Changes in Hemoglobin A1c Levels in Children Aged 4 to 6 Years

Abstract

Importance: Environmental risk factors for childhood type 2 diabetes, an increasing global problem, are understudied. Air pollution exposure has been reported to be a risk factor for this condition.

Objective: To examine the association between prenatal and perinatal exposures to fine particulate matter with a diameter less than 2.5 μm (PM2.5) and changes in hemoglobin A1c (HbA1c), a measure of glycated hemoglobin and marker of glucose dysregulation, in children aged 4 to 7 years.

Design, setting, and participants: The Programming Research in Obesity, Growth, Environment, and Social Stressors (PROGRESS) study, a birth cohort study conducted in Mexico City, Mexico, recruited pregnant women from July 3, 2007, to February 21, 2011, through public health maternity clinics. The present analysis includes 365 mother-child pairs followed up until the child was approximately 7 years of age. This study included data from only study visits at approximately 4 to 5 years (visit 1) and 6 to 7 years (visit 2) post partum because HbA1c levels were not measured in earlier visits. The data were analyzed from March 11, 2018, to May 3, 2019.

Exposures: Daily PM2.5 exposure estimates at participants' home addresses from 4 weeks prior to mothers' date of last menstrual period (LMP), a marker of the beginning of pregnancy, to 12 weeks after the due date. Exposure was estimated from satellite measurements and calibrated against ground PM2.5 measurements, land use, and meteorological variables.

Main outcomes and measures: Outcomes included HbA1c levels at 4 to 5 years and 6 to 7 years of age, and the change in the level from the former age group to the latter.

Results: The sample included 365 children, of whom 184 (50.4%) were girls. The mean (range) age of the children was 4.8 (4.0-6.4) years at visit 1, and 6.7 (6.0-9.7) years at visit 2. At the time of delivery, the mean (range) age of the mothers was 27.7 (18.3-44.4) years, with a mean (range) prepregnancy body mass index of 26.4 (18.5-43.5). The mean (SD) prenatal PM2.5 exposure (22.4 μg/m3 [2.7 μg/m3]) was associated with an annual increase in HbA1c levels of 0.25% (95% CI, 0.004%-0.50%) from age 4 to 5 years to 6 to 7 years compared with exposure at 12 μg/m3, the national regulatory standard in Mexico. Sex-specific effect estimates were statistically significant for girls (β = 0.21%; 95% CI, 0.10% to 0.32%) but not for boys (β = 0.31%; 95% CI, -0.09% to 0.72%). The statistically significant windows of exposure were from week 28 to 50.6 after the mother's LMP for the overall cohort and from week 11 to the end of the study period for girls. Lower HbA1c levels were observed at age 4 to 5 years in girls (β = -0.72%; 95% CI, -1.31% to -0.13%, exposure window from week 16 to 37.3) and boys (β = -0.98%; 95% CI, -1.70% to -0.26%, exposure window from the beginning of the study period to week 32.7), but no significant association was found in the overall cohort (β = -0.13%; 95% CI, -1.27% to 1.01%). There was no significant association between PM2.5 exposure and HbA1c level at age 6 to 7 years in any group.

Conclusions and relevance: The findings of this study suggest that prenatal and perinatal exposures to PM2.5 are associated with changes in HbA1c, which are indicative of glucose dysregulation, in early childhood. Further research is needed because this finding may represent a risk factor for childhood or adolescent diabetes.

Figure 1.. Density Plots of Estimates of Daily Exposure to Particulate Matter With Diameter Less Than 2.5 μm (PM_2.5) for All Participants

Individual daily estimates of prenatal PM_2.5 exposure were used for each of the 365 children in the cohort, resulting in 179 144 observations. The mean (SD) PM_2.5 exposure was 23.0 μg/m³ (2.7 μg/m³). Each continuous line in the density plot reflects 1 child’s exposures, and the density reflects the frequency of the exposure level for each child. The tails show that all children had very few days of exposure at that high level. Visual inspection of the density plots of each individual’s exposure showed no statistically significant outliers in the mean PM_2.5 exposure.

Figure 2.. Significant Exposure Windows and Effect Estimates for Association of Exposure to Particulate Matter With Diameter Less Than 2.5 μm (PM_2.5) With Changes in Hemoglobin A_1c (HbA_1c) Levels From Visit 1 to Visit 2

Associations are based on a PM_2.5 exposure of 23.0 μg/m³ compared with the cohort mean of 12 μg/m³. Shading indicates the 95% CIs. The x-axis of the exposure window plot depicts the week after last menstrual period (LMP) (0 is LMP), and the y-axis represents the association with HbA_1c level per day of PM_2.5 exposure (percentage change per day). The graphs show the point estimate for the change in HbA_1c (percentage) per year of exposure to PM_2.5. Error bars indicate 95% CIs.

Figure 3.. Significant Exposure Windows and Effect Estimates for Exposure to Particulate Matter With Diameter Less Than 2.5 μm (PM_2.5) on Hemoglobin A_1c (HbA_1c) Levels at Visit 1 and Visit 2

Associations are based on a PM_2.5 exposure of 23.0 μg/m³ compared with 12 μg/m³. Shading indicates the 95% CIs. The x-axis of the exposure window plot depicts the week after the last menstrual period (LMP) (0 is LMP), and the y-axis represents the association with HbA_1c per day of PM_2.5 exposure (percentage per day). The graphs show the point estimate for the association with HbA_1c (percentage) per year of exposure to PM_2.5. Error bars indicate 95% CIs.