Avoiding bias in self-controlled case series studies of coronavirus disease 2019
Avoiding bias in self-controlled case series studies of coronavirus disease 2019
复制标题
DOI：
10.1002/sim.9179
复制
发表时间：
2021-09-01
影响因子：
2
通讯作者：
Farrington, Paddy
中科院分区：
文献类型：
--
作者：
Fonseca-Rodriguez, Osvaldo;Connolly, Anne-Marie Fors;Farrington, Paddy
目前正在进行许多研究，包括自我对照病例系列研究，以量化感染导致2019冠状病毒病（COVID-19）的严重急性呼吸综合征冠状病毒2 （SARS-CoV-2）后并发症的风险。一项基于瑞典8个月期间出现的所有COVID-19病例的SCCS研究表明，SARS-CoV-2感染会增加AMI和缺血性中风的风险。SARS-CoV-2感染和COVID-19的一些特征出现在本研究中，也可能出现在其他研究中，使分析复杂化，并可能引入偏倚。在本文中，我们描述了这些特征，并探讨了它们可能产生的偏差。基于数据模拟的动机，我们提出了减少或消除这些偏差的方法。
Many studies, including self-controlled case series (SCCS) studies, are being undertaken to quantify the risks of complications following infection with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that causes coronavirus disease 2019 (COVID-19). One such SCCS study, based on all COVID-19 cases arising in Sweden over an 8-month period, has shown that SARS-CoV-2 infection increases the risks of AMI and ischemic stroke. Some features of SARS-CoV-2 infection and COVID-19, present in this study and likely in others, complicate the analysis and may introduce bias. In the present paper we describe these features, and explore the biases they may generate. Motivated by data-based simulations, we propose methods to reduce or remove these biases.