A Bayesian phase I/II clinical trial design in the presence of informative dropouts

Beibei Guo, Yong Zang, Ying Yuan

Research output: Contribution to journalArticle

Abstract

A phase I/II trial design utilizes both toxicity and efficacy outcomes to make the decision of dose assignment for patients. Because assessing the efficacy endpoint often requires a relatively long follow-up time, phase I/II trials are more susceptible to the missing data problem caused by informative dropouts that are correlated with treatment efficacy and toxicity. In addition, patient outcomes may not be scored quickly enough to apply decision rules that choose treatments or doses for newly accrued patients. To address these issues, we propose a Bayesian phase I/II design that jointly models efficacy, toxicity, and dropout as time-to-event data. Correlations among the three time-to-event outcomes are taken into account by a shared frailty. This joint model strategy accounts for the informative dropouts and has an additional advantage of accommodating a high accrual rate without suspending patient enrollment when toxicity or efficacy outcomes require a long follow-up. Under the Bayesian paradigm, we continuously update the posterior estimate of the model and assign incoming patients to the most desirable dose based on an efficacy-toxicity trade-off utility. Simulation studies show that the proposed design has good operating characteristics with a high probability of selecting the target dose and assigning the most patients to the target dose.

Original languageEnglish (US)
Pages (from-to)217-226
Number of pages10
JournalStatistics and its Interface
Volume8
Issue number2
DOIs
StatePublished - Jan 1 2015
Externally publishedYes

Fingerprint

Informative Dropout
Clinical Trials
Toxicity
Efficacy
Dose
Frailty
Joint Model
Target
Drop out
Operating Characteristics
Decision Rules
Missing Data
Assign
Design
Assignment
Choose
Trade-offs
Update
Paradigm
Simulation Study

Keywords

  • Bayesian adaptive design
  • Dose finding
  • Missing data
  • Nonignorable dropout
  • Trade-off

ASJC Scopus subject areas

  • Statistics and Probability
  • Applied Mathematics

Cite this

A Bayesian phase I/II clinical trial design in the presence of informative dropouts. / Guo, Beibei; Zang, Yong; Yuan, Ying.

In: Statistics and its Interface, Vol. 8, No. 2, 01.01.2015, p. 217-226.

Research output: Contribution to journalArticle

@article{d8a0bdc6e31749e5bb9d7df4905de541,
title = "A Bayesian phase I/II clinical trial design in the presence of informative dropouts",
abstract = "A phase I/II trial design utilizes both toxicity and efficacy outcomes to make the decision of dose assignment for patients. Because assessing the efficacy endpoint often requires a relatively long follow-up time, phase I/II trials are more susceptible to the missing data problem caused by informative dropouts that are correlated with treatment efficacy and toxicity. In addition, patient outcomes may not be scored quickly enough to apply decision rules that choose treatments or doses for newly accrued patients. To address these issues, we propose a Bayesian phase I/II design that jointly models efficacy, toxicity, and dropout as time-to-event data. Correlations among the three time-to-event outcomes are taken into account by a shared frailty. This joint model strategy accounts for the informative dropouts and has an additional advantage of accommodating a high accrual rate without suspending patient enrollment when toxicity or efficacy outcomes require a long follow-up. Under the Bayesian paradigm, we continuously update the posterior estimate of the model and assign incoming patients to the most desirable dose based on an efficacy-toxicity trade-off utility. Simulation studies show that the proposed design has good operating characteristics with a high probability of selecting the target dose and assigning the most patients to the target dose.",
keywords = "Bayesian adaptive design, Dose finding, Missing data, Nonignorable dropout, Trade-off",
author = "Beibei Guo and Yong Zang and Ying Yuan",
year = "2015",
month = "1",
day = "1",
doi = "10.4310/SII.2015.v8.n2.a9",
language = "English (US)",
volume = "8",
pages = "217--226",
journal = "Statistics and its Interface",
issn = "1938-7989",
publisher = "International Press of Boston, Inc.",
number = "2",

}

TY - JOUR

T1 - A Bayesian phase I/II clinical trial design in the presence of informative dropouts

AU - Guo, Beibei

AU - Zang, Yong

AU - Yuan, Ying

PY - 2015/1/1

Y1 - 2015/1/1

N2 - A phase I/II trial design utilizes both toxicity and efficacy outcomes to make the decision of dose assignment for patients. Because assessing the efficacy endpoint often requires a relatively long follow-up time, phase I/II trials are more susceptible to the missing data problem caused by informative dropouts that are correlated with treatment efficacy and toxicity. In addition, patient outcomes may not be scored quickly enough to apply decision rules that choose treatments or doses for newly accrued patients. To address these issues, we propose a Bayesian phase I/II design that jointly models efficacy, toxicity, and dropout as time-to-event data. Correlations among the three time-to-event outcomes are taken into account by a shared frailty. This joint model strategy accounts for the informative dropouts and has an additional advantage of accommodating a high accrual rate without suspending patient enrollment when toxicity or efficacy outcomes require a long follow-up. Under the Bayesian paradigm, we continuously update the posterior estimate of the model and assign incoming patients to the most desirable dose based on an efficacy-toxicity trade-off utility. Simulation studies show that the proposed design has good operating characteristics with a high probability of selecting the target dose and assigning the most patients to the target dose.

AB - A phase I/II trial design utilizes both toxicity and efficacy outcomes to make the decision of dose assignment for patients. Because assessing the efficacy endpoint often requires a relatively long follow-up time, phase I/II trials are more susceptible to the missing data problem caused by informative dropouts that are correlated with treatment efficacy and toxicity. In addition, patient outcomes may not be scored quickly enough to apply decision rules that choose treatments or doses for newly accrued patients. To address these issues, we propose a Bayesian phase I/II design that jointly models efficacy, toxicity, and dropout as time-to-event data. Correlations among the three time-to-event outcomes are taken into account by a shared frailty. This joint model strategy accounts for the informative dropouts and has an additional advantage of accommodating a high accrual rate without suspending patient enrollment when toxicity or efficacy outcomes require a long follow-up. Under the Bayesian paradigm, we continuously update the posterior estimate of the model and assign incoming patients to the most desirable dose based on an efficacy-toxicity trade-off utility. Simulation studies show that the proposed design has good operating characteristics with a high probability of selecting the target dose and assigning the most patients to the target dose.

KW - Bayesian adaptive design

KW - Dose finding

KW - Missing data

KW - Nonignorable dropout

KW - Trade-off

UR - http://www.scopus.com/inward/record.url?scp=84924417289&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84924417289&partnerID=8YFLogxK

U2 - 10.4310/SII.2015.v8.n2.a9

DO - 10.4310/SII.2015.v8.n2.a9

M3 - Article

VL - 8

SP - 217

EP - 226

JO - Statistics and its Interface

JF - Statistics and its Interface

SN - 1938-7989

IS - 2

ER -