Department of Environmental Sciences and Engineering, University of North Carolina, 135 Dauer Drive, Chapel Hill, NC 27599, USA.
Institute for Minority Health Research, University of Illinois at Chicago, 1819 W. Polk Street, Chicago, IL 60612, USA.
Environ Int. 2022 May;163:107176. doi: 10.1016/j.envint.2022.107176. Epub 2022 Mar 26.
Prenatal exposure to drinking water with arsenic concentrations >50 μg/L is associated with adverse birth outcomes, with inconclusive evidence for concentrations ≤50 μg/L. In a collaborative effort by public health experts, hydrologists, and geologists, we used published machine learning model estimates to characterize arsenic concentrations in private wells-federally unregulated for drinking water contaminants-and evaluated associations with birth outcomes throughout the conterminous U.S.
Using several machine learning models, including boosted regression trees (BRT) and random forest classification (RFC), developed from measured groundwater arsenic concentrations of ∼20,000 private wells, we characterized the probability that arsenic concentrations occurred within specific ranges in groundwater. Probabilistic model estimates and private well usage data were linked by county to all live birth certificates from 2016 (n = 3.6 million). We evaluated associations with gestational age and term birth weight using mixed-effects models, adjusted for potential confounders and incorporated random intercepts for spatial clustering.
We generally observed inverse associations with term birth weight. For instance, when using BRT estimates, a 10-percentage point increase in the probability that private well arsenic concentrations exceeded 5 μg/L was associated with a -1.83 g (95% CI: -3.30, -0.38) lower term birth weight after adjusting for covariates. Similarly, a 10-percentage point increase in the probability that private well arsenic concentrations exceeded 10 μg/L was associated with a -2.79 g (95% CI: -4.99, -0.58) lower term birth weight. Associations with gestational age were null.
In this largest epidemiologic study of arsenic and birth outcomes to date, we did not observe associations of modeled arsenic estimates in private wells with gestational age and found modest inverse associations with term birth weight. Study limitations may have obscured true associations, including measurement error stemming from a lack of individual-level information on primary water sources, water arsenic concentrations, and water consumption patterns.
产前暴露于砷浓度超过 50μg/L 的饮用水与不良出生结局相关，而浓度低于 50μg/L 的饮用水与不良出生结局的关系尚无定论。在公共卫生专家、水文学家和地质学家的合作下，我们使用已发表的机器学习模型估计值来描述私人井水的砷浓度——这些井水不受联邦饮用水污染物法规的监管，并评估了其与整个美国的出生结局之间的关联。
我们使用了几种机器学习模型，包括增强回归树（BRT）和随机森林分类（RFC），这些模型是基于大约 20000 口私人井水的实测地下水砷浓度开发的，我们描述了地下水砷浓度处于特定范围内的概率。概率模型估计值和私人井使用数据通过县与 2016 年的所有活产出生证明（n=360 万）相关联。我们使用混合效应模型评估了与胎龄和足月出生体重的关联，调整了潜在的混杂因素，并纳入了空间聚类的随机截距。
我们通常观察到与足月出生体重呈负相关。例如，当使用 BRT 估计值时，私人井水砷浓度超过 5μg/L 的概率每增加 10%，在调整了协变量后，足月出生体重会降低 1.83g（95%CI：-3.30，-0.38）。同样，当私人井水砷浓度超过 10μg/L 的概率每增加 10%，足月出生体重会降低 2.79g（95%CI：-4.99，-0.58）。与胎龄的关联为零。
在迄今为止最大的砷与出生结局的流行病学研究中，我们没有观察到私人井中建模砷估计值与胎龄的关联，并且发现与足月出生体重呈适度的负相关。研究的局限性可能掩盖了真实的关联，包括由于缺乏关于主要水源、水砷浓度和水消费模式的个体水平信息而导致的测量误差。
