Methods for generalizing inferences from cluster randomized controlled trials to target populations

将整群随机对照试验的推论推广到目标人群的方法

• 批准号: 10563184
• 负责人: Issa J. Dahabreh
• 金额: $ 34.01万
• 依托单位: HARVARD SCHOOL OF PUBLIC HEALTH
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-02-04 至 2025-12-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10563184
• 关键词: Accounting; Address; Adjuvant; Affect; Clinical; Data; Data Collection; Data Science; Dependence; Dose; Eligibility Determination; Enrollment; Funding; Healthcare Systems; Individual; Influenza vaccination; Intervention; Investments; Knowledge; Machine Learning; Methodology; Methods; Modeling; Modernization; Nursing Homes; Outcome; Participant; Performance; Policies; Population; Randomized; Randomized, Controlled Trials; Recombinants; Research; Research Design; Research Personnel; Sample Size; Statistical Methods; Structure; Target Populations; Uncertainty; United States National Institutes of Health; cluster trial; deep learning; design; flexibility; follow-up; influenza virus vaccine; interest; machine learning method; novel; novel strategies; optimal treatments; practice setting; random forest; randomized trial; response; routine care; routine practice; simulation; support vector machine; tool; treatment effect; treatment strategy; vaccination strategy

PROJECT SUMMARY/ABSTRACT Cluster trials are the study design of choice when interventions are best applied at the group level and when exposure of one individual may affect the outcomes of other individuals in the same cluster. Cluster trials are increasingly embedded within large health care systems, allowing the use of routinely collected data to increase research efficiency. There is concern, however – and this proposal provides supportive evidence – that randomized clusters are not representative the target populations seen in routine care. When treatment effects vary over factors that influence trial participation, treatment effects from the trial cannot be directly applied to real-world target populations of substantive interest. Thus, even in well-designed cluster trials, selective participation can lead to bias in drawing causal inferences about the target population. Given the increasing number of cluster trials being conducted, investigators need rigorous methods for generalizing findings from cluster trials to target populations that address selective participation bias and can account for multiple data science challenges, including stochastic dependence among observations in the same cluster; availability of randomized trial data from only a few clusters or from clusters with relatively small sample sizes; lack of knowledge of predictors of trial participation and the outcome, when candidate covariates often exceed the number of available clusters and necessitate the use of flexible machine learning approaches; and missing outcome data. In response to Notice of Special Interest NOT-LM-19-003, we propose novel, domain- independent, reusable causal and statistical methods to address these data-science challenges and to increase the ability of cluster trials to inform clinical and policy decisions by eliminating bias due to selective participation when estimating average treatment effects and when estimating the optimal covariate-dependent treatment strategy. We will evaluate the methods in realistic simulation studies and in empirical analyses using data from 3 large-scale cluster trials of influenza vaccination strategies in U.S. nursing homes.

项目摘要/摘要 群集试验是当最好在小组级别和何时采用干预措施时的研究设计 一个人的暴露可能会影响同一集群中其他人的结果。集群试验是 越来越多地嵌入大型医疗保健系统中，允许使用常规收集的数据 但是，人们担心 - 该提案提供了支持的证据 - 那个随机簇不能代表常规护理中看到的目标种群。治疗时 影响因影响试验参与的因素而异，试验的治疗效果不能直接 应用于现实世界中具有实质性关注的目标人群。即使在精心设计的集群试验中， 选择性参与会导致偏向对目标人群的因果推断。鉴于 进行的集群试验数量增加，研究人员需要严格的方法来概括 集群试验的发现到目标人群，以解决选择性参与偏见，并可以考虑 多个数据科学挑战，包括同一群集中观察结果之间的随机依赖性； 仅来自几个群集或样本量相对较小的簇的随机试验数据； 缺乏对试验参与预测因素和结果的了解，当候选协变量经常超过 可用的群集的数量以及必要的使用灵活的机器学习方法；和失踪 结果数据。为了回应特殊兴趣的通知，而不是-19-003，我们提出了新颖的领域 - 独立，可重复使用的因果和统计方法，以应对这些数据科学挑战，并 通过消除选择性的偏见来提高集群试验为临床和政策决策提供信息的能力 当估计平均治疗效果以及估计最佳协变量依赖性时参与 治疗策略。我们将评估使用现实的仿真研究和使用经验分析的方法 来自美国护士住宅中的3个大规模疫苗接种策略的大规模集群试验的数据。