Huang Ying, Prentice Ross L
Biostatistics, Bioinformatics & Epidemiology Program, Vaccine & Infectious Diseases Division, Fred Hutchinson Cancer Center, 1100 Fairview Ave N, Seattle, WA, 98109, United States.
Biostatistics Program, Public Health Science Division, Fred Hutchinson Cancer Center, 1100 Fairview Ave N, Seattle, WA, 98109, United States.
Biostatistics. 2024 Dec 31;26(1). doi: 10.1093/biostatistics/kxaf014.
In nutritional epidemiology, self-reported dietary data are commonly used to investigate diet-disease relationships. However, the resulting association estimates are often subject to biases due to random and systematic measurement errors. Regression calibration has emerged as a crucial method for addressing these biases by refining self-reported nutrient intake with objective biomarkers, which differ from the true values only by a random "noise" component. This paper presents methodological tools for analyzing nutritional epidemiology cohort studies involving time-to-event data when a biomarker subsample is available alongside dietary assessments. We introduce novel regression calibration methods to tackle two common challenges in this field. First, a widely used approach assumes that the log hazard ratio (HR) follows a linear function of dietary exposure. However, assessing whether this assumption holds-or if a more flexible model is needed to capture potential deviations from linearity-is often necessary. Second, another prevalent analytical strategy involves estimating HRs based on categorized dietary exposure variables. New methods are critically needed to minimize bias in defining category boundaries and estimating hazard ratios within exposure categories, both of which can be distorted by measurement error. We apply these methods to reassess the relationship between sodium and potassium intake and cardiovascular disease risk using data from the Women's Health Initiative.
在营养流行病学中，自我报告的饮食数据常用于研究饮食与疾病的关系。然而，由于随机和系统测量误差，由此得出的关联估计值往往存在偏差。回归校准已成为一种关键方法，通过使用客观生物标志物来优化自我报告的营养素摄入量，从而解决这些偏差，客观生物标志物与真实值的差异仅在于随机“噪声”成分。本文介绍了在有生物标志物子样本与饮食评估同时可用的情况下，分析涉及事件发生时间数据的营养流行病学队列研究的方法工具。我们引入了新颖的回归校准方法来应对该领域的两个常见挑战。首先，一种广泛使用的方法假设对数风险比（HR）遵循饮食暴露的线性函数。然而，评估该假设是否成立——或者是否需要更灵活的模型来捕捉与线性的潜在偏差——通常是必要的。其次，另一种普遍的分析策略涉及基于分类的饮食暴露变量估计风险比。迫切需要新的方法来最小化定义类别边界和估计暴露类别内风险比时的偏差，这两者都可能因测量误差而失真。我们应用这些方法，利用女性健康倡议的数据重新评估钠和钾摄入量与心血管疾病风险之间的关系。
