Two-stage marker-stratified clinical trial design in the presence of biomarker misclassification

Yong Zang, J. Jack Lee, Ying Yuan

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The marker-stratified design (MSD) is an important design to assess treatment and marker effects in personalized medicine. The MSD stratifies patients into marker positive and marker negative subgroups on the basis of their biomarker profiles and then randomizes them to the standard treatment or a new treatment within each subgroup. The performance of the MSD can be seriously undermined when the biomarker is measured with error (or misclassified). A recently proposed analytic method corrects the biomarker misclassification in the MSD under the assumptions that the biomarker classification rates are known and no other covariates need to be adjusted. We propose a two-stage MSD to relax these assumptions. We analytically investigate the bias in the estimation of prognostic and predictive marker effects and treatment effects caused by biomarker misclassification in the presence of covariates, and we propose an expectation–maximization algorithm to correct such biases. The design does not require prespecification of the misclassification rates and can incorporate any covariates that potentially confound the prognostic and predictive marker effects and treatment effect. Numerical trial applications show that the method has desirable operating characteristics.

Original languageEnglish (US)
Pages (from-to)585-601
Number of pages17
JournalJournal of the Royal Statistical Society. Series C: Applied Statistics
Volume65
Issue number4
DOIs
StatePublished - Aug 1 2016
Externally publishedYes

Fingerprint

Misclassification
Biomarkers
Clinical Trials
Covariates
Treatment Effects
Subgroup
Misclassification Rate
Operating Characteristics
Expectation-maximization Algorithm
Design
Clinical trials
Medicine

Keywords

  • Clinical trial
  • Expectation–maximization algorithm
  • Marker-stratified design
  • Misclassification
  • Molecularly targeted agent
  • Personalized medicine

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

Two-stage marker-stratified clinical trial design in the presence of biomarker misclassification. / Zang, Yong; Jack Lee, J.; Yuan, Ying.

In: Journal of the Royal Statistical Society. Series C: Applied Statistics, Vol. 65, No. 4, 01.08.2016, p. 585-601.

Research output: Contribution to journalArticle

@article{97c514070858465dbfbbae1ddda33d30,
title = "Two-stage marker-stratified clinical trial design in the presence of biomarker misclassification",
abstract = "The marker-stratified design (MSD) is an important design to assess treatment and marker effects in personalized medicine. The MSD stratifies patients into marker positive and marker negative subgroups on the basis of their biomarker profiles and then randomizes them to the standard treatment or a new treatment within each subgroup. The performance of the MSD can be seriously undermined when the biomarker is measured with error (or misclassified). A recently proposed analytic method corrects the biomarker misclassification in the MSD under the assumptions that the biomarker classification rates are known and no other covariates need to be adjusted. We propose a two-stage MSD to relax these assumptions. We analytically investigate the bias in the estimation of prognostic and predictive marker effects and treatment effects caused by biomarker misclassification in the presence of covariates, and we propose an expectation–maximization algorithm to correct such biases. The design does not require prespecification of the misclassification rates and can incorporate any covariates that potentially confound the prognostic and predictive marker effects and treatment effect. Numerical trial applications show that the method has desirable operating characteristics.",
keywords = "Clinical trial, Expectation–maximization algorithm, Marker-stratified design, Misclassification, Molecularly targeted agent, Personalized medicine",
author = "Yong Zang and {Jack Lee}, J. and Ying Yuan",
year = "2016",
month = "8",
day = "1",
doi = "10.1111/rssc.12140",
language = "English (US)",
volume = "65",
pages = "585--601",
journal = "Journal of the Royal Statistical Society. Series C: Applied Statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - Two-stage marker-stratified clinical trial design in the presence of biomarker misclassification

AU - Zang, Yong

AU - Jack Lee, J.

AU - Yuan, Ying

PY - 2016/8/1

Y1 - 2016/8/1

N2 - The marker-stratified design (MSD) is an important design to assess treatment and marker effects in personalized medicine. The MSD stratifies patients into marker positive and marker negative subgroups on the basis of their biomarker profiles and then randomizes them to the standard treatment or a new treatment within each subgroup. The performance of the MSD can be seriously undermined when the biomarker is measured with error (or misclassified). A recently proposed analytic method corrects the biomarker misclassification in the MSD under the assumptions that the biomarker classification rates are known and no other covariates need to be adjusted. We propose a two-stage MSD to relax these assumptions. We analytically investigate the bias in the estimation of prognostic and predictive marker effects and treatment effects caused by biomarker misclassification in the presence of covariates, and we propose an expectation–maximization algorithm to correct such biases. The design does not require prespecification of the misclassification rates and can incorporate any covariates that potentially confound the prognostic and predictive marker effects and treatment effect. Numerical trial applications show that the method has desirable operating characteristics.

AB - The marker-stratified design (MSD) is an important design to assess treatment and marker effects in personalized medicine. The MSD stratifies patients into marker positive and marker negative subgroups on the basis of their biomarker profiles and then randomizes them to the standard treatment or a new treatment within each subgroup. The performance of the MSD can be seriously undermined when the biomarker is measured with error (or misclassified). A recently proposed analytic method corrects the biomarker misclassification in the MSD under the assumptions that the biomarker classification rates are known and no other covariates need to be adjusted. We propose a two-stage MSD to relax these assumptions. We analytically investigate the bias in the estimation of prognostic and predictive marker effects and treatment effects caused by biomarker misclassification in the presence of covariates, and we propose an expectation–maximization algorithm to correct such biases. The design does not require prespecification of the misclassification rates and can incorporate any covariates that potentially confound the prognostic and predictive marker effects and treatment effect. Numerical trial applications show that the method has desirable operating characteristics.

KW - Clinical trial

KW - Expectation–maximization algorithm

KW - Marker-stratified design

KW - Misclassification

KW - Molecularly targeted agent

KW - Personalized medicine

UR - http://www.scopus.com/inward/record.url?scp=84978945319&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978945319&partnerID=8YFLogxK

U2 - 10.1111/rssc.12140

DO - 10.1111/rssc.12140

M3 - Article

AN - SCOPUS:84978945319

VL - 65

SP - 585

EP - 601

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

IS - 4

ER -