A multi-source adaptive platform design for testing sequential combinatorial therapeutic strategies

Alexander M. Kaizer, Brian P. Hobbs, Joe Koopmeiners

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Traditional paradigms for clinical translation are challenged in settings where multiple contemporaneous therapeutic strategies have been identified as potentially beneficial. Platform trials have emerged as an approach for sequentially comparing multiple trials using a single protocol. The Ebola virus disease outbreak in West Africa represents one recent example which utilized a platform design. Specifically, the PREVAIL II master protocol sequentially tested new combinations of therapies against the concurrent, optimal standard of care (oSOC) strategy. Once a treatment demonstrated sufficient evidence of benefit, the treatment was added to the oSOC for all future comparisons (denoted as segments throughout the manuscript). In the interest of avoiding bias stemming from population drift, PREVAIL II considered only within-segment comparisons between the oSOC and novel treatments and failed to leverage data from oSOC patients in prior segments. This article describes adaptive design methodology aimed at boosting statistical power through Bayesian modeling and adaptive randomization. Specifically, the design uses multi-source exchangeability models to combine data from multiple segments and adaptive randomization to achieve information balance within a segment. When compared to the PREVAIL II design, we demonstrate that our proposed adaptive platform design improves power by as much as 51% with limited type-I error inflation. Further, the adaptive platform effectuates more balance with respect to the distribution of acquired information among study arms, with more patients randomized to experimental regimens.

Original languageEnglish (US)
Pages (from-to)1082-1094
Number of pages13
JournalBiometrics
Volume74
Issue number3
DOIs
StatePublished - Sep 1 2018

Fingerprint

Sequential Testing
Standard of Care
therapeutics
Testing
Random Allocation
Randomisation
testing
Ebola Hemorrhagic Fever
Ebolavirus
Therapeutics
Exchangeability
Bayesian Modeling
Adaptive Design
Statistical Power
Western Africa
patient care
Manuscripts
Information Dissemination
Type I error
inflation

Keywords

  • Adaptive randomization
  • Ebola virus disease
  • Emerging infectious diseases
  • Multi-source smoothing
  • Platform design

Cite this

A multi-source adaptive platform design for testing sequential combinatorial therapeutic strategies. / Kaizer, Alexander M.; Hobbs, Brian P.; Koopmeiners, Joe.

In: Biometrics, Vol. 74, No. 3, 01.09.2018, p. 1082-1094.

Research output: Contribution to journalArticle

Kaizer, Alexander M. ; Hobbs, Brian P. ; Koopmeiners, Joe. / A multi-source adaptive platform design for testing sequential combinatorial therapeutic strategies. In: Biometrics. 2018 ; Vol. 74, No. 3. pp. 1082-1094.
@article{ad146155a3cc424285bd870dfe1abf5f,
title = "A multi-source adaptive platform design for testing sequential combinatorial therapeutic strategies",
abstract = "Traditional paradigms for clinical translation are challenged in settings where multiple contemporaneous therapeutic strategies have been identified as potentially beneficial. Platform trials have emerged as an approach for sequentially comparing multiple trials using a single protocol. The Ebola virus disease outbreak in West Africa represents one recent example which utilized a platform design. Specifically, the PREVAIL II master protocol sequentially tested new combinations of therapies against the concurrent, optimal standard of care (oSOC) strategy. Once a treatment demonstrated sufficient evidence of benefit, the treatment was added to the oSOC for all future comparisons (denoted as segments throughout the manuscript). In the interest of avoiding bias stemming from population drift, PREVAIL II considered only within-segment comparisons between the oSOC and novel treatments and failed to leverage data from oSOC patients in prior segments. This article describes adaptive design methodology aimed at boosting statistical power through Bayesian modeling and adaptive randomization. Specifically, the design uses multi-source exchangeability models to combine data from multiple segments and adaptive randomization to achieve information balance within a segment. When compared to the PREVAIL II design, we demonstrate that our proposed adaptive platform design improves power by as much as 51{\%} with limited type-I error inflation. Further, the adaptive platform effectuates more balance with respect to the distribution of acquired information among study arms, with more patients randomized to experimental regimens.",
keywords = "Adaptive randomization, Ebola virus disease, Emerging infectious diseases, Multi-source smoothing, Platform design",
author = "Kaizer, {Alexander M.} and Hobbs, {Brian P.} and Joe Koopmeiners",
year = "2018",
month = "9",
day = "1",
doi = "10.1111/biom.12841",
language = "English (US)",
volume = "74",
pages = "1082--1094",
journal = "Biometrics",
issn = "0006-341X",
publisher = "Wiley-Blackwell",
number = "3",

}

TY - JOUR

T1 - A multi-source adaptive platform design for testing sequential combinatorial therapeutic strategies

AU - Kaizer, Alexander M.

AU - Hobbs, Brian P.

AU - Koopmeiners, Joe

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Traditional paradigms for clinical translation are challenged in settings where multiple contemporaneous therapeutic strategies have been identified as potentially beneficial. Platform trials have emerged as an approach for sequentially comparing multiple trials using a single protocol. The Ebola virus disease outbreak in West Africa represents one recent example which utilized a platform design. Specifically, the PREVAIL II master protocol sequentially tested new combinations of therapies against the concurrent, optimal standard of care (oSOC) strategy. Once a treatment demonstrated sufficient evidence of benefit, the treatment was added to the oSOC for all future comparisons (denoted as segments throughout the manuscript). In the interest of avoiding bias stemming from population drift, PREVAIL II considered only within-segment comparisons between the oSOC and novel treatments and failed to leverage data from oSOC patients in prior segments. This article describes adaptive design methodology aimed at boosting statistical power through Bayesian modeling and adaptive randomization. Specifically, the design uses multi-source exchangeability models to combine data from multiple segments and adaptive randomization to achieve information balance within a segment. When compared to the PREVAIL II design, we demonstrate that our proposed adaptive platform design improves power by as much as 51% with limited type-I error inflation. Further, the adaptive platform effectuates more balance with respect to the distribution of acquired information among study arms, with more patients randomized to experimental regimens.

AB - Traditional paradigms for clinical translation are challenged in settings where multiple contemporaneous therapeutic strategies have been identified as potentially beneficial. Platform trials have emerged as an approach for sequentially comparing multiple trials using a single protocol. The Ebola virus disease outbreak in West Africa represents one recent example which utilized a platform design. Specifically, the PREVAIL II master protocol sequentially tested new combinations of therapies against the concurrent, optimal standard of care (oSOC) strategy. Once a treatment demonstrated sufficient evidence of benefit, the treatment was added to the oSOC for all future comparisons (denoted as segments throughout the manuscript). In the interest of avoiding bias stemming from population drift, PREVAIL II considered only within-segment comparisons between the oSOC and novel treatments and failed to leverage data from oSOC patients in prior segments. This article describes adaptive design methodology aimed at boosting statistical power through Bayesian modeling and adaptive randomization. Specifically, the design uses multi-source exchangeability models to combine data from multiple segments and adaptive randomization to achieve information balance within a segment. When compared to the PREVAIL II design, we demonstrate that our proposed adaptive platform design improves power by as much as 51% with limited type-I error inflation. Further, the adaptive platform effectuates more balance with respect to the distribution of acquired information among study arms, with more patients randomized to experimental regimens.

KW - Adaptive randomization

KW - Ebola virus disease

KW - Emerging infectious diseases

KW - Multi-source smoothing

KW - Platform design

UR - http://www.scopus.com/inward/record.url?scp=85047798041&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047798041&partnerID=8YFLogxK

U2 - 10.1111/biom.12841

DO - 10.1111/biom.12841

M3 - Article

VL - 74

SP - 1082

EP - 1094

JO - Biometrics

JF - Biometrics

SN - 0006-341X

IS - 3

ER -