Bayesian kernel machine regression for estimating the health effects of multi-pollutant mixtures
Bayesian kernel machine regression for estimating the health effects of multi-pollutant mixtures
复制标题
DOI：
10.1093/biostatistics/kxu058
复制
发表时间：
2015-07-01
期刊：
影响因子：
2.1
通讯作者：
Coull, Brent A.
中科院分区：
文献类型：
--
作者：
Bobb, Jennifer F.;Valeri, Linda;Coull, Brent A.
由于人类总是暴露于复杂的化学混合物中，因此估计多污染物暴露的健康影响是环境流行病学和美国环境保护署等监管机构的关键问题。然而，大多数健康影响研究都集中在单一因素或考虑简单的双向相互作用模型，部分原因是我们缺乏统计方法来更真实地捕捉混合暴露的复杂性。我们引入贝叶斯核机器回归（BKMR）作为一种新的方法来研究混合物，其中的健康结果回归的灵活功能的混合物（例如，空气污染或有毒废物）的组成部分，指定使用核函数。在高维环境中，一种新的分层变量选择方法被纳入到识别重要的混合物成分和占相关的混合物结构。模拟研究表明，成功的BKMR在估计的安全响应函数，并在确定负责健康影响的混合物的各个组成部分。我们通过流行病学和毒理学应用展示了该方法的特点。
Because humans are invariably exposed to complex chemical mixtures, estimating the health effects of multi-pollutant exposures is of critical concern in environmental epidemiology, and to regulatory agencies such as the U.S. Environmental Protection Agency. However, most health effects studies focus on single agents or consider simple two-way interaction models, in part because we lack the statistical methodology to more realistically capture the complexity of mixed exposures. We introduce Bayesian kernel machine regression (BKMR) as a new approach to study mixtures, in which the health outcome is regressed on a flexible function of the mixture (e.g. air pollution or toxic waste) components that is specified using a kernel function. In high-dimensional settings, a novel hierarchical variable selection approach is incorporated to identify important mixture components and account for the correlated structure of the mixture. Simulation studies demonstrate the success of BKMR in estimating the exposure-response function and in identifying the individual components of the mixture responsible for health effects. We demonstrate the features of the method through epidemiology and toxicology applications.