Construction of environmental risk score beyond standard linear models using machine learning methods: application to metal mixtures, oxidative stress and cardiovascular disease in NHANES.
Construction of environmental risk score beyond standard linear models using machine learning methods: application to metal mixtures, oxidative stress and cardiovascular disease in NHANES.
复制标题
DOI：
10.1186/s12940-017-0310-9
复制
发表时间：
2017-09-26
期刊：
影响因子：
--
通讯作者：
Mukherjee B
中科院分区：
文献类型：
--
作者：
Park SK;Zhao Z;Mukherjee B
人们越来越关注接触污染物混合物对健康的影响。我们最初提出了一个环境风险评分（ERS）作为一个总结措施，以检查在流行病学研究中暴露于多种污染物的风险，只考虑污染物的主要影响。我们扩大ERS考虑污染物-污染物的相互作用，使用现代机器学习方法。我们说明了多污染物的方法来预测氧化应激的标志物（γ-谷氨酰转移酶（GGT）），一种常见的疾病途径连接环境暴露和许多健康终点。我们检查了来自国家健康和营养检查调查（NHANES 2003-2004至2013-2014，n = 9664）的6个周期的尿液或全血中测量的20种金属生物标志物。我们随机将数据均匀地分成训练集和测试集，并在训练集中使用具有主效应和成对相互作用的自适应弹性网络（AENET-I），贝叶斯添加剂回归树（BART），贝叶斯核机器回归（BKMR）和超级学习器构建金属混合物的ERS用于GGT，并评估其在测试集中的性能。我们还评估了GGT-ERS与心血管终点之间的相关性。基于AENET-I的ERS在测试集的预测误差方面优于其他方法。与GGT相关的重要金属包括镉（尿）、二甲基胂酸、单甲基胂酸、钴和钡。所有ERS均显示与收缩压、舒张压和高血压显著相关。对于高血压，AENET-I、BART和SuperLearner的每个ERS增加一个SD，比值比分别为1.26（95% CI，1.15，1.38）、1.17（1.09，1.25）和1.30（1.20，1.40）。ERS与死亡率结果无显著正相关。地球资源卫星是描述污染物混合物累积风险特征的有用工具，可解决统计方面的挑战，如高度相关性和污染物-污染物相互作用。为中间标记物如GGT构建的ERS可预测相关疾病终点。本文的在线版本（10.1186/s12940-017-0310-9）包含补充材料，可供授权用户使用。
There is growing concern of health effects of exposure to pollutant mixtures. We initially proposed an Environmental Risk Score (ERS) as a summary measure to examine the risk of exposure to multi-pollutants in epidemiologic research considering only pollutant main effects. We expand the ERS by consideration of pollutant-pollutant interactions using modern machine learning methods. We illustrate the multi-pollutant approaches to predicting a marker of oxidative stress (gamma-glutamyl transferase (GGT)), a common disease pathway linking environmental exposure and numerous health endpoints. We examined 20 metal biomarkers measured in urine or whole blood from 6 cycles of the National Health and Nutrition Examination Survey (NHANES 2003–2004 to 2013–2014, n = 9664). We randomly split the data evenly into training and testing sets and constructed ERS’s of metal mixtures for GGT using adaptive elastic-net with main effects and pairwise interactions (AENET-I), Bayesian additive regression tree (BART), Bayesian kernel machine regression (BKMR), and Super Learner in the training set and evaluated their performances in the testing set. We also evaluated the associations between GGT-ERS and cardiovascular endpoints. ERS based on AENET-I performed better than other approaches in terms of prediction errors in the testing set. Important metals identified in relation to GGT include cadmium (urine), dimethylarsonic acid, monomethylarsonic acid, cobalt, and barium. All ERS’s showed significant associations with systolic and diastolic blood pressure and hypertension. For hypertension, one SD increase in each ERS from AENET-I, BART and SuperLearner were associated with odds ratios of 1.26 (95% CI, 1.15, 1.38), 1.17 (1.09, 1.25), and 1.30 (1.20, 1.40), respectively. ERS’s showed non-significant positive associations with mortality outcomes. ERS is a useful tool for characterizing cumulative risk from pollutant mixtures, with accounting for statistical challenges such as high degrees of correlations and pollutant-pollutant interactions. ERS constructed for an intermediate marker like GGT is predictive of related disease endpoints. The online version of this article (10.1186/s12940-017-0310-9) contains supplementary material, which is available to authorized users.
登录
查看更多内容
影响因子：
2.5
作者：
DRAPER, NR;VANNOSTRAND, RC
通讯作者：
VANNOSTRAND, RC
影响因子：
2.8
作者：
Agarwal, Shikhar;Zaman, Tarique;Kapadia, Samir R.
通讯作者：
Kapadia, Samir R.
评估对化学混合物和癌症风险建模的加权分位数总和回归的评估。
影响因子：
2
作者：
Czarnota J;Gennings C;Wheeler DC
通讯作者：
Wheeler DC
DOI：
10.1109/34.709601
发表时间：
1998-08-01
影响因子：
23.6
作者：
Ho, TK
通讯作者：
Ho, TK
影响因子：
3.3
作者：
Janicki-Deverts D;Cohen S;Matthews KA;Gross MD;Jacobs DR Jr
通讯作者：
Jacobs DR Jr