Multi-Stage Adaptive Enrichment Trials Public Deposited

Last Modified
  • March 19, 2019
  • Joshi, Neha
    • Affiliation: Gillings School of Global Public Health, Department of Biostatistics
  • We first consider the problem of estimating a biomarker-based subgroup and testing for treatment effect in the overall population and in the subgroup after the trial. We define the best subgroup as the subgroup that maximizes the power for comparing the experimental treatment with the control. In the case of continuous outcome and a single biomarker, both a non-parametric method of estimating the subgroup and a method based on fitting a linear model with treatment by biomarker interaction to the data perform well. Several procedures for testing for treatment effect in all and in the subgroup are discussed. Cross-validation with two cohorts is used to estimate the biomarker cut-off to determine the best subgroup and to test for treatment effect. An approach that combines the tests in all patients and in the subgroup using Hochberg’s method is recommended. This test performs well in the case when there is a subgroup with sizable treatment effect and in the case when the treatment is beneficial to everyone. We also consider the problem of estimating the best subgroup and testing for treatment effect prospectively in a clinical trial. We define the best subgroup as the subgroup that maximizes a utility function that reflects the trade-off between the subgroup size and the treatment effect. For subgroup estimation in trials with moderate effects sizes and sample sizes, simpler methods, such as linear regression, work better than more complex tree-based approaches. We propose a three-stage enrichment design, where the subgroup is estimated at the first interim analysis and then refined in the second interim analysis, along with a futility analysis. A weighted inverse normal combination test is used to test the hypothesis of no treatment effect across the three stages. Additionally, we consider a problem of subgroup estimation based on a multivariate outcome in both parallel group and crossover trials. We compare three methods of defining and estimating the best subgroup: a method based on the average and the maximum of the outcomes and the method based on the p-value for the treatment comparison.
Date of publication
Resource type
  • Fine, Jason
  • Couper, David
  • Baron, John
  • Suchindran, Chirayath
  • Ivanova, Anastasia
  • Doctor of Philosophy
Degree granting institution
  • University of North Carolina at Chapel Hill Graduate School
Graduation year
  • 2019

This work has no parents.