Subgroup selection in adaptive signature designs of confirmatory clinical trials

Zhiwei Zhang, Meijuan Li, Min Lin, Guoxing Soon, Tom Greene, Changyu Shen

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The increasing awareness of treatment effect heterogeneity has motivated flexible designs of confirmatory clinical trials that prospectively allow investigators to test for treatment efficacy for a subpopulation of patients in addition to the entire population. If a target subpopulation is not well characterized in the design stage, it can be developed at the end of a broad eligibility trial under an adaptive signature design. The paper proposes new procedures for subgroup selection and treatment effect estimation (for the selected subgroup) under an adaptive signature design. We first provide a simple and general characterization of the optimal subgroup that maximizes the power for demonstrating treatment efficacy or the expected gain based on a specified utility function. This characterization motivates a procedure for subgroup selection that involves prediction modelling, augmented inverse probability weighting and low dimensional maximization. A cross-validation procedure can be used to remove or reduce any resubstitution bias that may result from subgroup selection, and a bootstrap procedure can be used to make inference about the treatment effect in the subgroup selected. The approach proposed is evaluated in simulation studies and illustrated with real examples.

Original languageEnglish (US)
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
DOIs
StateAccepted/In press - 2016

Fingerprint

Clinical Trials
Signature
Subgroup
Treatment Effects
Efficacy
Inverse Probability Weighting
Utility Function
Cross-validation
Bootstrap
Design
Clinical trials
Maximise
Simulation Study
Entire
Treatment effects
Target
Prediction
Modeling

Keywords

  • Cross-validation
  • Personalized medicine
  • Predictive biomarker
  • Subgroup analysis
  • Treatment effect heterogeneity

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Subgroup selection in adaptive signature designs of confirmatory clinical trials. / Zhang, Zhiwei; Li, Meijuan; Lin, Min; Soon, Guoxing; Greene, Tom; Shen, Changyu.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, 2016.

Research output: Contribution to journalArticle

Zhang, Zhiwei ; Li, Meijuan ; Lin, Min ; Soon, Guoxing ; Greene, Tom ; Shen, Changyu. / Subgroup selection in adaptive signature designs of confirmatory clinical trials. In: Journal of the Royal Statistical Society. Series C: Applied Statistics. 2016.
@article{d97142236ee147739b3987f98e56df7a,
title = "Subgroup selection in adaptive signature designs of confirmatory clinical trials",
abstract = "The increasing awareness of treatment effect heterogeneity has motivated flexible designs of confirmatory clinical trials that prospectively allow investigators to test for treatment efficacy for a subpopulation of patients in addition to the entire population. If a target subpopulation is not well characterized in the design stage, it can be developed at the end of a broad eligibility trial under an adaptive signature design. The paper proposes new procedures for subgroup selection and treatment effect estimation (for the selected subgroup) under an adaptive signature design. We first provide a simple and general characterization of the optimal subgroup that maximizes the power for demonstrating treatment efficacy or the expected gain based on a specified utility function. This characterization motivates a procedure for subgroup selection that involves prediction modelling, augmented inverse probability weighting and low dimensional maximization. A cross-validation procedure can be used to remove or reduce any resubstitution bias that may result from subgroup selection, and a bootstrap procedure can be used to make inference about the treatment effect in the subgroup selected. The approach proposed is evaluated in simulation studies and illustrated with real examples.",
keywords = "Cross-validation, Personalized medicine, Predictive biomarker, Subgroup analysis, Treatment effect heterogeneity",
author = "Zhiwei Zhang and Meijuan Li and Min Lin and Guoxing Soon and Tom Greene and Changyu Shen",
year = "2016",
doi = "10.1111/rssc.12175",
language = "English (US)",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",

}

TY - JOUR

T1 - Subgroup selection in adaptive signature designs of confirmatory clinical trials

AU - Zhang, Zhiwei

AU - Li, Meijuan

AU - Lin, Min

AU - Soon, Guoxing

AU - Greene, Tom

AU - Shen, Changyu

PY - 2016

Y1 - 2016

N2 - The increasing awareness of treatment effect heterogeneity has motivated flexible designs of confirmatory clinical trials that prospectively allow investigators to test for treatment efficacy for a subpopulation of patients in addition to the entire population. If a target subpopulation is not well characterized in the design stage, it can be developed at the end of a broad eligibility trial under an adaptive signature design. The paper proposes new procedures for subgroup selection and treatment effect estimation (for the selected subgroup) under an adaptive signature design. We first provide a simple and general characterization of the optimal subgroup that maximizes the power for demonstrating treatment efficacy or the expected gain based on a specified utility function. This characterization motivates a procedure for subgroup selection that involves prediction modelling, augmented inverse probability weighting and low dimensional maximization. A cross-validation procedure can be used to remove or reduce any resubstitution bias that may result from subgroup selection, and a bootstrap procedure can be used to make inference about the treatment effect in the subgroup selected. The approach proposed is evaluated in simulation studies and illustrated with real examples.

AB - The increasing awareness of treatment effect heterogeneity has motivated flexible designs of confirmatory clinical trials that prospectively allow investigators to test for treatment efficacy for a subpopulation of patients in addition to the entire population. If a target subpopulation is not well characterized in the design stage, it can be developed at the end of a broad eligibility trial under an adaptive signature design. The paper proposes new procedures for subgroup selection and treatment effect estimation (for the selected subgroup) under an adaptive signature design. We first provide a simple and general characterization of the optimal subgroup that maximizes the power for demonstrating treatment efficacy or the expected gain based on a specified utility function. This characterization motivates a procedure for subgroup selection that involves prediction modelling, augmented inverse probability weighting and low dimensional maximization. A cross-validation procedure can be used to remove or reduce any resubstitution bias that may result from subgroup selection, and a bootstrap procedure can be used to make inference about the treatment effect in the subgroup selected. The approach proposed is evaluated in simulation studies and illustrated with real examples.

KW - Cross-validation

KW - Personalized medicine

KW - Predictive biomarker

KW - Subgroup analysis

KW - Treatment effect heterogeneity

UR - http://www.scopus.com/inward/record.url?scp=84992388230&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992388230&partnerID=8YFLogxK

U2 - 10.1111/rssc.12175

DO - 10.1111/rssc.12175

M3 - Article

JO - Journal of the Royal Statistical Society. Series C: Applied Statistics

JF - Journal of the Royal Statistical Society. Series C: Applied Statistics

SN - 0035-9254

ER -