Tools to help patients and other stakeholders' input into choice of estimand and intercurrent event strategy in randomised trials
MRC Clinical Trials Unit at UCL, UCL(伦敦大学学院医学研究委员会临床试验单元);Department of Biostatistics and Health Informatics, Institute of Psychiatry, Psychology and Neuroscience, King's College London(伦敦国王学院精神病学、心理学和神经科学研究所生物统计与健康信息学系);Aberdeen Centre for Evaluation, University of Aberdeen(阿伯丁大学阿伯丁评估中心);Imperial Clinical Trials Unit, School of Public Health, Imperial College London(帝国理工学院公共卫生学院帝国临床试验单元)
Joanna Hindley, Charlotte Hartley, Jennifer Hellier, Kate Sturgeon, Sophie Greenwood, Ian Newsome, Katherine Barrett, Debs Smith, Tra My Pham, Dongquan Bi, Beat… 展开作者
Joanna Hindley, Charlotte Hartley, Jennifer Hellier, Kate Sturgeon, Sophie Greenwood, Ian Newsome, Katherine Barrett, Debs Smith, Tra My Pham, Dongquan Bi, Beatriz Goulao, Suzie Cro, Brennan C Kahan
Estimands can help to clarify the research questions being addressed in randomised trials. Because the choice of estimand can affect how relevant trial results are to patients and other stakeholders, such as clinicians or policymakers, it is important for them to be involved in these decisions. However, there are barriers to having these conversations. For instance, discussions around how intercurrent events should be addressed in the estimand definition typically involve complex concepts as well as technical language. We three tools to facilitate conversations between researchers and patients and other stakeholders about the choice of estimand and intercurrent event strategy: (i) a video explaining the concept of an estimand and the five different ways that intercurrent events can be incorporated into the estimand definition; (ii) an infographic outlining these five strategies; and (iii) an editable PowerPoint slide which can be completed with trial-specific details to facilitate conversations around choice of estimand for a particular trial. These resources can help to start conversations between the trial team and patients and other stakeholders about the best choice of estimand and intercurrent event strategies for a randomised trial.
Hypothetical estimands in clinical trials: a unification of causal inference and missing data methods
ICH E9附录引入了术语并发事件,是指随机化后发生的事件,这些事件可能妨碍观察到关注的结局或影响其解释。它提出了五种处理并发事件的策略,以形成一个被估量,但没有提出估计的统计方法。在本文中,我们专注于假设的策略,其中的处理效应的假设情况下,其中并发事件是防止定义。对于它的估计,我们考虑了因果推断和缺失数据方法。我们建立了某些“因果推断估计量”是相同的某些“缺失数据估计量”。这些链接可能会帮助那些熟悉一套方法而不是另一套方法的人。此外,使用潜在结果符号使我们能够更清楚地说明缺失数据方法依赖于哪些假设来估计假设被估量。这有助于表明估计假设的被估量是否合理,以及在分析中应该使用什么数据。我们发现,假设的被估量可以估计并发事件发生后,这是通常不使用的数据利用。我们还提出了蒙特卡罗模拟,说明在不同的设置中的方法的实施和性能。
Estimands and Their Implications for Evidence Synthesis for Oncology: A Simulation Study of Treatment Switching in Meta-Analysis
Core Clinical Sciences Inc.;Centre for Advancing Health Outcomes, University of British Columbia(不列颠哥伦比亚大学健康结果促进中心);Novo Nordisk Pharma(诺和诺德制药);Novo Nordisk A/S(诺和诺德公司);KeeneONStatistics;Department of Health Research Methodology, Evidence, and Impact, McMaster University(麦克马斯特大学健康研究方法、证据与影响系)
Applying the estimands framework to non-inferiority trials: guidance on choice of hypothetical estimands for non-adherence and comparison of estimation methods
Bayesian analysis of the causal reference-based model for missing data in clinical trials, accommodating partially observed post-intercurrent event data
London School of Hygiene and Tropical Medicine(伦敦卫生与热带医学学院);Roche, Basel, Switzerland(罗氏,瑞士巴塞尔)
Estimands and their Estimators for Clinical Trials Impacted by the COVID-19 Pandemic: A Report from the NISS Ingram Olkin Forum Series on Unplanned Clinical Trial Disruptions
Estimating the treatment effect for adherers using multiple imputation
随机对照试验被认为是评价处理效应(被估量)的有效性和安全性的金标准。根据最近的国际协调理事会(ICH)-E9附录(R1),在定义被估量时需要考虑并发事件(ICE),主层是处理ICE的五种策略之一。Qu et al.(2020,Statistics in Biopharmacology Research 12:1 - 18)提出了粘附者平均因果效应(AdACE)的估计量,用于估计基于因果推理框架坚持一种或两种治疗的患者的治疗差异,并证明了这些估计量的一致性;然而,该方法需要与高维数值积分相关的复杂自定义编程。在本文中,我们使用多重插补(MI)实现了AdACE估计量,并通过自举构造CI。一项模拟研究表明,基于MI的估计量为关注的依从人群的治疗差异提供了具有CI标称覆盖概率的相合估计量。作为一个说明性的例子,新方法被应用于一个真实的临床试验的数据,比较2种类型的基础胰岛素对1型糖尿病患者。
Weighted Approach for Estimating Effects in Principal Strata with Missing Data for a Categorical Post-Baseline Variable in Randomized Controlled Trials