Analysis Models for Multi-regional Clinical Trials

Li, Gang; Quan, Hui; Lan, Gordon

doi:10.1201/9781003109785-11

Cited by 4 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For continuous and binary endpoints in NI designs which test the null hypothesis of treatment inferiority in difference by the NI margin (denoted as that is a positive number), the consistency probability [7] can be calculated as:…”

Section: Non-inferiority Designmentioning

confidence: 99%

RegionSizeR – A novel app for regional sample size planning in MRCTs

Sun,

et al. 2024

Preprint

View full text Add to dashboard Cite

In multi-regional clinical trials, planning the sample size for participating regions is essential for the evaluation of the treatment effect consistency across regions. Based on the MRCT design and sample size allocation to regions, consistency probability is usually used to predict the consistent trend between regions and the overall population, while preserving a certain proportion of the overall treatment effect. Specific enrollment characteristics in a region of interest should also be considered in the meantime of the sample size planning. To facilitate efficient and harmonized regional sample size planning, we have developed RegionSizeR, a comprehensive and user-friendly interactive web-based R shiny application that can be obtained from https://github.com/rsr-ss/RegionSizeR. This simulation-based app can serve as an initial point for discussions on sample size allocation plans, following preservation of treatment effect method in ICH E17. The app accommodates various types of endpoints and designs, including continuous, binary, and time-to-event endpoints, for superiority, non-inferiority, and MCP-Mod designs. To ensure the validity of this app, independent testing is conducted allowing a discrepancy of no more than 1%.

show abstract

Section: Non-inferiority Designmentioning

confidence: 99%

RegionSizeR – A novel app for regional sample size planning in MRCTs

Sun,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The CREM assumes that region-specific treatment effects are samples from an underlying normal distribution, whereas the DREM assumes that regional sample sizes jointly follow a multinomial distribution. Depending on how regions are defined or if regional samples sizes are predetermined (e.g., based on regional regulatory requirements), these assumptions about the random effects may not be valid for an MRCT, and the model performances can be sensitive to the accuracy of these assumptions and the magnitude of the between-region variability (Li et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Bayesian multiregional clinical trials using model averaging

2021

View full text Add to dashboard Cite

Summary Multiregional clinical trials (MRCTs) provide the benefit of more rapidly introducing drugs to the global market; however, small regional sample sizes can lead to poor estimation quality of region-specific effects when using current statistical methods. With the publication of the International Conference for Harmonisation E17 guideline in 2017, the MRCT design is recognized as a viable strategy that can be accepted by regional regulatory authorities, necessitating new statistical methods that improve the quality of region-specific inference. In this article, we develop a novel methodology for estimating region-specific and global treatment effects for MRCTs using Bayesian model averaging. This approach can be used for trials that compare two treatment groups with respect to a continuous outcome, and it allows for the incorporation of patient characteristics through the inclusion of covariates. We propose an approach that uses posterior model probabilities to quantify evidence in favor of consistency of treatment effects across all regions, and this metric can be used by regulatory authorities for drug approval. We show through simulations that the proposed modeling approach results in lower MSE than a fixed-effects linear regression model and better control of type I error rates than a Bayesian hierarchical model.

show abstract