Interim Analyses During Group Sequential Clinical Trials

Meurer, William J; Tolles, Juliana

doi:10.1001/jama.2021.10174

Cited by 15 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The benefits and limitations of interim futility analyses have been well documented [21][22][23]. Incorporating a futility assessment can increase the efficiency of the trial, allowing trials that are unlikely to meet their objectives to stop early ultimately reducing costs, preserving resources, and limiting patient burden.…”

Section: Discussionmentioning

confidence: 99%

Guidance on interim analysis methods in clinical trials

Ciolino

Kaizer

Bonner

2023

J. Clin. Trans. Sci.

View full text Add to dashboard Cite

Interim analyses in clinical trials can take on a multitude of forms. They are often used to guide Data and Safety Monitoring Board (DSMB) recommendations to study teams regarding recruitment targets for large, later-phase clinical trials. As collaborative biostatisticians working and teaching in multiple fields of research and across a broad array of trial phases, we note the large heterogeneity and confusion surrounding interim analyses in clinical trials. Thus, in this paper, we aim to provide a general overview and guidance on interim analyses for a nonstatistical audience. We explain each of the following types of interim analyses: efficacy, futility, safety, and sample size re-estimation, and we provide the reader with reasoning, examples, and implications for each. We emphasize that while the types of interim analyses employed may differ depending on the nature of the study, we would always recommend prespecification of the interim analytic plan to the extent possible with risk mitigation and trial integrity remaining a priority. Finally, we posit that interim analyses should be used as tools to help the DSMB make informed decisions in the context of the overarching study. They should generally not be deemed binding, and they should not be reviewed in isolation.

show abstract

Section: Discussionmentioning

confidence: 99%

Guidance on interim analysis methods in clinical trials

Ciolino

Kaizer

Bonner

2023

J. Clin. Trans. Sci.

View full text Add to dashboard Cite

show abstract

“…The CONSERVE guidelines extend the CONSORT and SPIRIT guidelines by addressing how to report extenuating circumstances that lead to a modification in trial design, conduct, or analysis . Many articles have focused on the methods for appropriately conducting and reporting interim analyses of trial data . In contrast, clear guidance has been lacking for reporting the circumstances and actions when modifications in a clinical trial are based on external events.…”

Section: What Are the Conserve Guidelines?mentioning

confidence: 99%

Assessing Unexpected Circumstances That Lead to Modifications in Clinical Trial Design, Conduct, or Analysis

Brooks

Wisniewski

2022

JAMA

View full text Add to dashboard Cite

“…In the case of a failed phase 3 trial in which there is evidence of a beneficial but not statistically significant effect of vaccination, one possibility to speed licensure of the vaccine would be to incorporate data from the initial trial into the analysis of data from a new, smaller trial [6,7]. This could be conducted as a traditional trial with a fixed sample size or, potentially more efficiently, as a group sequential Bayesian trial [8]. With group sequential trials, vaccine efficacy (VE) is evaluated on an ongoing basis during interim evaluations, and the trial is stopped when sufficient evidence of efficacy has been collected [8,9].…”

Section: Introductionmentioning

confidence: 99%

“…This could be conducted as a traditional trial with a fixed sample size or, potentially more efficiently, as a group sequential Bayesian trial [8]. With group sequential trials, vaccine efficacy (VE) is evaluated on an ongoing basis during interim evaluations, and the trial is stopped when sufficient evidence of efficacy has been collected [8,9]. In the case of a post-licensure evaluation of vaccine effectiveness, estimates from the phase 3 trial could be integrated into analyses that confirm the study results of safety or efficacy.…”

Section: Introductionmentioning

confidence: 99%

Incorporating efficacy data from initial trials into subsequent evaluations: Application to vaccines against respiratory syncytial virus

Sundaram

Pitzer

Omer

et al. 2023

Preprint

View full text Add to dashboard Cite

Background. When a randomized controlled trial fails to demonstrate statistical efficacy against the primary endpoint, a costly new trial would need to be conducted to receive a license. Partially incorporating data from previous trials might allow for the conduct of a more efficient follow-up trial to demonstrate efficacy, speeding the availability of effective vaccines. Methods Based on the outcomes from a failed trial of a maternal vaccine against respiratory syncytial virus (RSV), we simulated data for a new Bayesian group-sequential trial. The data were analyzed either ignoring data from the previous trial (minimally informative priors) or using priors that partially incorporate the historical data into the analysis. We evaluated scenarios where the efficacy in the new trial was the same, greater than, or less than the efficacy in the original trial. For each scenario, we evaluated the frequentist power and Type I error following interim analyses. Results If a stringent threshold is used to control Type I error, the analyses that incorporated historical data had a small advantage over trials that did not. If control of Type I error is less important (e.g., in a post-licensure evaluation), the incorporation of historical data can provide a substantial boost in efficiency. Conclusions. Due to the need to control Type I error in a trial used to license a vaccine, the incorporation of historical data provides little additional benefit in terms of stopping the trial early. However, these statistical approaches could be promising in evaluations that use real-world evidence following licensure.

show abstract

Interim Analyses During Group Sequential Clinical Trials

Abstract: This JAMA Guide to Statistics and Methods describes why interim analyses are performed during group sequential trials, provides examples of the limitations of interim analyses, and provides guidance on interpreting the results of interim analyses performed during group sequential trials.

Cited by 15 publications

References 10 publications

Guidance on interim analysis methods in clinical trials

Guidance on interim analysis methods in clinical trials

Assessing Unexpected Circumstances That Lead to Modifications in Clinical Trial Design, Conduct, or Analysis

Incorporating efficacy data from initial trials into subsequent evaluations: Application to vaccines against respiratory syncytial virus

Contact Info

Product

Resources

About