Bayesian adaptive randomized trial design for patients with recurrent glioblastoma

Lorenzo Trippa, Eudocia Q. Lee, Patrick Y. Wen, Tracy T. Batchelor, Timothy Cloughesy, Giovanni Parmigiani, Brian M. Alexander

Research output: Contribution to journalArticle

Abstract

Purpose: To evaluate whether the use of Bayesian adaptive randomized (AR) designs in clinical trials for glioblastoma is feasible and would allow for more efficient trials. Patients and Methods: We generated an adaptive randomization procedure that was retrospectively applied to primary patient data from four separate phase II clinical trials in patients with recurrent glioblastoma. We then compared AR designs with more conventional trial designs by using realistic hypothetical scenarios consistent with survival data reported in the literature. Our primary end point was the number of patients needed to achieve a desired statistical power. Results: If our phase II trials had been a single, multiarm trial using AR design, 30 fewer patients would have been needed compared with a multiarm balanced randomized (BR) design to attain the same power level. More generally, Bayesian AR trial design for patients with glioblastoma would result in trials with fewer overall patients with no loss in statistical power and in more patients being randomly assigned to effective treatment arms. For a 140-patient trial with a control arm, two ineffective arms, and one effective arm with a hazard ratio of 0.6, a median of 47 patients would be randomly assigned to the effective arm compared with 35 in a BR trial design. Conclusion: Given the desire for control arms in phase II trials, an increasing number of experimental therapeutics, and a relatively short time for events, Bayesian AR designs are attractive for clinical trials in glioblastoma.

Original languageEnglish (US)
Pages (from-to)3258-3263
Number of pages6
JournalJournal of Clinical Oncology
Volume30
Issue number26
DOIs
StatePublished - Sep 10 2012
Externally publishedYes

Fingerprint

Glioblastoma
Clinical Trials
Phase II Clinical Trials
Random Allocation
Survival
Therapeutics

ASJC Scopus subject areas

  • Cancer Research
  • Oncology

Cite this

Trippa, L., Lee, E. Q., Wen, P. Y., Batchelor, T. T., Cloughesy, T., Parmigiani, G., & Alexander, B. M. (2012). Bayesian adaptive randomized trial design for patients with recurrent glioblastoma. Journal of Clinical Oncology, 30(26), 3258-3263. https://doi.org/10.1200/JCO.2011.39.8420

Bayesian adaptive randomized trial design for patients with recurrent glioblastoma. / Trippa, Lorenzo; Lee, Eudocia Q.; Wen, Patrick Y.; Batchelor, Tracy T.; Cloughesy, Timothy; Parmigiani, Giovanni; Alexander, Brian M.

In: Journal of Clinical Oncology, Vol. 30, No. 26, 10.09.2012, p. 3258-3263.

Research output: Contribution to journalArticle

Trippa, L, Lee, EQ, Wen, PY, Batchelor, TT, Cloughesy, T, Parmigiani, G & Alexander, BM 2012, 'Bayesian adaptive randomized trial design for patients with recurrent glioblastoma', Journal of Clinical Oncology, vol. 30, no. 26, pp. 3258-3263. https://doi.org/10.1200/JCO.2011.39.8420
Trippa L, Lee EQ, Wen PY, Batchelor TT, Cloughesy T, Parmigiani G et al. Bayesian adaptive randomized trial design for patients with recurrent glioblastoma. Journal of Clinical Oncology. 2012 Sep 10;30(26):3258-3263. https://doi.org/10.1200/JCO.2011.39.8420
Trippa, Lorenzo ; Lee, Eudocia Q. ; Wen, Patrick Y. ; Batchelor, Tracy T. ; Cloughesy, Timothy ; Parmigiani, Giovanni ; Alexander, Brian M. / Bayesian adaptive randomized trial design for patients with recurrent glioblastoma. In: Journal of Clinical Oncology. 2012 ; Vol. 30, No. 26. pp. 3258-3263.
@article{500832a12a96454588d2059aecf0d582,
title = "Bayesian adaptive randomized trial design for patients with recurrent glioblastoma",
abstract = "Purpose: To evaluate whether the use of Bayesian adaptive randomized (AR) designs in clinical trials for glioblastoma is feasible and would allow for more efficient trials. Patients and Methods: We generated an adaptive randomization procedure that was retrospectively applied to primary patient data from four separate phase II clinical trials in patients with recurrent glioblastoma. We then compared AR designs with more conventional trial designs by using realistic hypothetical scenarios consistent with survival data reported in the literature. Our primary end point was the number of patients needed to achieve a desired statistical power. Results: If our phase II trials had been a single, multiarm trial using AR design, 30 fewer patients would have been needed compared with a multiarm balanced randomized (BR) design to attain the same power level. More generally, Bayesian AR trial design for patients with glioblastoma would result in trials with fewer overall patients with no loss in statistical power and in more patients being randomly assigned to effective treatment arms. For a 140-patient trial with a control arm, two ineffective arms, and one effective arm with a hazard ratio of 0.6, a median of 47 patients would be randomly assigned to the effective arm compared with 35 in a BR trial design. Conclusion: Given the desire for control arms in phase II trials, an increasing number of experimental therapeutics, and a relatively short time for events, Bayesian AR designs are attractive for clinical trials in glioblastoma.",
author = "Lorenzo Trippa and Lee, {Eudocia Q.} and Wen, {Patrick Y.} and Batchelor, {Tracy T.} and Timothy Cloughesy and Giovanni Parmigiani and Alexander, {Brian M.}",
year = "2012",
month = "9",
day = "10",
doi = "10.1200/JCO.2011.39.8420",
language = "English (US)",
volume = "30",
pages = "3258--3263",
journal = "Journal of Clinical Oncology",
issn = "0732-183X",
publisher = "American Society of Clinical Oncology",
number = "26",

}

TY - JOUR

T1 - Bayesian adaptive randomized trial design for patients with recurrent glioblastoma

AU - Trippa, Lorenzo

AU - Lee, Eudocia Q.

AU - Wen, Patrick Y.

AU - Batchelor, Tracy T.

AU - Cloughesy, Timothy

AU - Parmigiani, Giovanni

AU - Alexander, Brian M.

PY - 2012/9/10

Y1 - 2012/9/10

N2 - Purpose: To evaluate whether the use of Bayesian adaptive randomized (AR) designs in clinical trials for glioblastoma is feasible and would allow for more efficient trials. Patients and Methods: We generated an adaptive randomization procedure that was retrospectively applied to primary patient data from four separate phase II clinical trials in patients with recurrent glioblastoma. We then compared AR designs with more conventional trial designs by using realistic hypothetical scenarios consistent with survival data reported in the literature. Our primary end point was the number of patients needed to achieve a desired statistical power. Results: If our phase II trials had been a single, multiarm trial using AR design, 30 fewer patients would have been needed compared with a multiarm balanced randomized (BR) design to attain the same power level. More generally, Bayesian AR trial design for patients with glioblastoma would result in trials with fewer overall patients with no loss in statistical power and in more patients being randomly assigned to effective treatment arms. For a 140-patient trial with a control arm, two ineffective arms, and one effective arm with a hazard ratio of 0.6, a median of 47 patients would be randomly assigned to the effective arm compared with 35 in a BR trial design. Conclusion: Given the desire for control arms in phase II trials, an increasing number of experimental therapeutics, and a relatively short time for events, Bayesian AR designs are attractive for clinical trials in glioblastoma.

AB - Purpose: To evaluate whether the use of Bayesian adaptive randomized (AR) designs in clinical trials for glioblastoma is feasible and would allow for more efficient trials. Patients and Methods: We generated an adaptive randomization procedure that was retrospectively applied to primary patient data from four separate phase II clinical trials in patients with recurrent glioblastoma. We then compared AR designs with more conventional trial designs by using realistic hypothetical scenarios consistent with survival data reported in the literature. Our primary end point was the number of patients needed to achieve a desired statistical power. Results: If our phase II trials had been a single, multiarm trial using AR design, 30 fewer patients would have been needed compared with a multiarm balanced randomized (BR) design to attain the same power level. More generally, Bayesian AR trial design for patients with glioblastoma would result in trials with fewer overall patients with no loss in statistical power and in more patients being randomly assigned to effective treatment arms. For a 140-patient trial with a control arm, two ineffective arms, and one effective arm with a hazard ratio of 0.6, a median of 47 patients would be randomly assigned to the effective arm compared with 35 in a BR trial design. Conclusion: Given the desire for control arms in phase II trials, an increasing number of experimental therapeutics, and a relatively short time for events, Bayesian AR designs are attractive for clinical trials in glioblastoma.

UR - http://www.scopus.com/inward/record.url?scp=84866627568&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866627568&partnerID=8YFLogxK

U2 - 10.1200/JCO.2011.39.8420

DO - 10.1200/JCO.2011.39.8420

M3 - Article

C2 - 22649140

AN - SCOPUS:84866627568

VL - 30

SP - 3258

EP - 3263

JO - Journal of Clinical Oncology

JF - Journal of Clinical Oncology

SN - 0732-183X

IS - 26

ER -