Division of Epidemiology and Biostatistics, School of Public Health, University of Illinois at Chicago, Chicago; University of Illinois Cancer Center, University of Illinois Hospital and Health Sciences System, Chicago.
Division of Epidemiology and Biostatistics, School of Public Health, University of Illinois at Chicago, Chicago.
Ann Epidemiol. 2020 Nov;51:35-40.e1. doi: 10.1016/j.annepidem.2020.07.010. Epub 2020 Jul 22.
This study examined potential sources of selection and information biases when using residence history information from a commercial database to construct residential histories for cancer research.
We searched the LexisNexis database for residence data on 3473 adults diagnosed with cancers of the prostate, colon/rectum, and female breast in a single health-care system between 2005 and 2016 using the name and address at diagnosis and the birth date. Residential histories were generated from the results using open-source statistical programs from the National Cancer Institute. Multivariable regression models analyzed the associations of the search results with demographic characteristics and all-cause mortality.
Racial/ethnic minorities were less likely to match to vendor residence data compared with non-Hispanic whites (odd ratios [95% confidence intervals (CIs)] for non-Hispanic blacks, Hispanics, and Asian/Pacific Islander were 1.66 [1.30, 2.12], 2.92 [2.18, 3.90], and 4.53 [2.72, 7.55], respectively). Being non-Hispanic black was negatively associated with years of residential history (vs. non-Hispanic whites, β coefficient [95% CI] = -2.57 [-3.40, -1.73]). Not matching to residence data was associated with an increased 5-year odds of death from any cause (vs. matched subjects, odd ratios [95% CI] = 5.92 [4.29, 8.50]).
Differential ascertainment of residence history by race/ethnicity and association of ascertainment with prognosis are potential sources of selection and information biases when using residence data from a commercial database.
本研究旨在探讨利用商业数据库中的居住史信息构建癌症研究居住史时，可能存在的选择和信息偏倚来源。
我们在单一医疗系统中，利用诊断时的姓名和地址以及出生日期，在 LexisNexis 数据库中检索了 2005 年至 2016 年间 3473 名被诊断患有前列腺癌、结肠癌/直肠癌和乳腺癌的成年人的居住数据。使用美国国立癌症研究所的开源统计程序从检索结果中生成居住史。多变量回归模型分析了检索结果与人口统计学特征和全因死亡率之间的关联。
与非西班牙裔白人相比，少数族裔被认为不太可能与供应商居住数据相匹配（非西班牙裔黑人、西班牙裔和亚洲/太平洋岛民的比值[95%置信区间（CI）]分别为 1.66[1.30, 2.12]、2.92[2.18, 3.90]和 4.53[2.72, 7.55]）。非西班牙裔黑人与居住史年限呈负相关（与非西班牙裔白人相比，β系数[95%CI]为-2.57[-3.40, -1.73]）。与居住数据不匹配与任何原因导致的 5 年死亡风险增加相关（与匹配的受试者相比，比值比[95%CI]为 5.92[4.29, 8.50]）。
在使用商业数据库中的居住数据时，种族/民族对居住史的不同确定以及与预后的关联可能是选择和信息偏倚的潜在来源。
