A new approach to a legacy concern: Evaluating machine-learned Bayesian networks to predict childhood lead exposure risk from community water systems
A new approach to a legacy concern: Evaluating machine-learned Bayesian networks to predict childhood lead exposure risk from community water systems
复制标题
DOI：
10.1016/j.envres.2021.112146
复制
发表时间：
2021-09-30
影响因子：
8.3
通讯作者：
Gibson, Jacqueline MacDonald
中科院分区：
文献类型：
--
作者：
Mulhern, Riley;Roostaei, Javad;Gibson, Jacqueline MacDonald
饮用水中的铅继续使儿童面临不可逆转的神经损伤的风险。需要了解影响血铅水平的饮用水系统特征，以防止持续暴露。这项研究试图利用机器学习的贝叶斯网络来评估儿童血铅水平与饮用水系统特征之间的关系。北卡罗来纳州威克县 2003 年至 2017 年 40,742 名儿童的血铅记录与 178 个社区供水系统的特征以及每个儿童所在社区的社会人口特征进行了匹配。通过机器学习贝叶斯网络来评估与血铅水平 >2 μg/dL 和 >5 μg/dL 相关的饮用水变量。该模型用于预测铅暴露风险增加的地理区域和供水设施。饮用水特征与儿童血铅水平>5μg/dL没有显着相关性，但却是血铅水平>2μg/dL的重要预测因素。血液检测前的最近一年中，是否有 10% 的水样铅含量超过 2 ppb，是最重要的水系统预测指标，并且会使血铅水平 >2 μg/dL 的风险增加 42%。该模型在十倍交叉验证期间获得了 0.792 (+/- 0.8%) 的受试者工作特征曲线下面积，表明具有良好的预测性能。因此，水系统特征可用于预测存在较高血铅水平风险的区域。目前的饮用水铅监管阈值可能不足以检测饮用水中与儿童血铅水平相关的水平。
Lead in drinking water continues to put children at risk of irreversible neurological impairment. Understanding drinking water system characteristics that influence blood lead levels is needed to prevent ongoing exposures. This study sought to assess the relationship between children's blood lead levels and drinking water system characteristics using machine-learned Bayesian networks. Blood lead records from 2003 to 2017 for 40,742 children in Wake County, North Carolina were matched with the characteristics of 178 community water systems and sociodemographic characteristics of each child's neighborhood. Bayesian networks were machine-learned to evaluate the drinking water variables associated with blood lead levels >2 mu g/dL and >5 mu g/dL. The model was used to predict geographic areas and water utilities with increased lead exposure risk. Drinking water characteristics were not significantly associated with children's blood lead levels >5 mu g/dL but were important predictors of blood lead levels >2 mu g/dL. Whether 10% of water samples exceeded 2 ppb of lead in the most recent year prior to the blood test was the most important water system predictor and increased the risk of blood lead levels >2 mu g/dL by 42%. The model achieved an area under the receiver operating characteristic curve of 0.792 (+/- 0.8%) during ten-fold cross validation, indicating good predictive performance. Water system characteristics may thus be used to predict areas that are at risk of higher blood lead levels. Current drinking water regulatory thresholds for lead may be insufficient to detect the levels in drinking water associated with children's blood lead levels.