Measurement Errors in Environmental Epidemiology

描述（由申请方提供）：暴露测量误差是几乎所有环境和流行病学研究中偏倚的一个可能来源，通常会导致相对风险估计不足和检测效应的统计功效丧失。在本项目的上一个周期中，我们扩展了多元回归模型（包括考克斯模型和logistic模型）中测量误差调整的回归校准方法，以适应环境流行病学中遇到的研究设计和数据结构。我们在许多关于内毒素、甲基叔丁基醚、铅和室内NO2环境暴露对健康影响的出版物中介绍了这些新方法，并开发了公开可用的软件。在该项目的下一个周期，我们将重点关注空气污染流行病学问题，特别是颗粒暴露和元素碳对全因死亡率、心血管死亡率和肺癌死亡率的慢性影响。在组建了一个由来自世界各地的领先统计学家、环境科学家和环境流行病学家组成的跨学科团队后，我们将开发方法来调整考克斯回归模型中的测量误差，该模型适用于六个城市研究、护士健康研究、荷兰队列研究和MESA-Air的前瞻性队列设计，涉及累积和12个月运行平均暴露指标。将仔细关注暴露时间和暴露度量的剂量-反应曲线的潜在非线性的重要问题，特别是消除由于暴露测量误差而导致的这些特征量化中的偏倚。NHS和MESA-AIR中可用的生物标志物数据将用于改进暴露验证。方便用户使用的软件将在网上公布，以便于大规模应用新方法。 公共卫生相关性：根据最近的研究推断，美国每年约有10万例过早死亡可能与暴露于空气中的颗粒物有关。对有关接触空气污染成分的有限数据的解释表明，长期接触的影响似乎大大大于急性接触的影响。已发现替代暴露度量的测量误差很大，但统计工具无法在分析中明确调整此偏倚来源。我们建议开发这样做的方法，并将其应用于四个主要的研究空气污染与死亡率：六个城市的研究，护士的健康研究，MESA-Air，和荷兰队列研究。这些分析将大大提高我们对暴露于空气污染的健康影响的认识，包括确定暴露的关键时间和暴露-反应关系中的潜在非线性，并将有助于未来的风险评估和政策制定。

DESCRIPTION (provided by applicant): Exposure measurement error is a likely source of bias in nearly all environmental and epidemiological studies, typically leading to under-estimation of relative risks and loss of statistical power to detect effects. In the previous cycle of this project, we extended the regression calibration method for adjustment for measurement error in multivariate regression models, including Cox models and logistic models, to accommodate the study designs and data structures encountered in environmental epidemiology. We featured these new methods in a number of publications on the health effects of environmental exposure to endotoxin, methyl tert-butyl ether, lead, and indoor NO2, and developed publicly available software. In the next cycle of this project, we will focus on issues in air pollution epidemiology - in particular, the chronic effects of particulate exposure and elemental carbon on all-cause mortality, cardio-vascular mortality and lung cancer mortality. Having assembled an inter-disciplinary team of leading statisticians, environmental scientists and environmental epidemiologists from around the world, we will develop methods to adjust for measurement error in Cox regression models suitable for the prospective cohort designs of the Six Cities Study, Nurses' Health Study, Netherlands Cohort Study, and MESA-Air in relation to cumulative and 12 month running average exposure metrics. Careful attention will be paid to the important issues surrounding timing of exposure and potential non-linearity of the dose-response curves of the exposure metrics, in particular, removing bias in the quantification of these features due to exposure measurement error. The biomarker data available in NHS and MESA-AIR will be used to improve the exposure validation. User- friendly software will be posted on the web, facilitating widescale application of the new methods. PUBLIC HEALTH RELEVANCE: Extrapolation from recent studies has suggested that approximately 100,000 premature deaths in the United States may be associated with exposure to airborne particles each year. Interpretation of the limited data on exposure to constituents of air pollution suggests that the effects of long-term exposure appear to be substantially greater than those of acute exposure. Measurement error in alternative exposure metrics has been found to be substantial, yet the statistical tools are not available to adjust for this source of bias explicitly in analysis. We propose to develop methods for doing this, and apply them to four major studies on air pollution in relation to mortality: the Six Cities Study, the Nurses' Health Study, MESA-Air, and the Netherlands Cohort Study. These analyses will substantially improve our understanding of the health effects of exposure to air pollution, including identification of the critical times of exposure and potential non-linearity in the exposure-response relationship, and will be useful in future risk assessment and policy development.