Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials

Byron J. Gajewski, Caitlyn Meinzer, Scott M. Berry, Gaylan L. Rockswold, William G. Barsan, Frederick Korley, Renee H. Martin

Research output: Contribution to journalArticle

Abstract

A primary goal of a phase II dose-ranging trial is to identify a correct dose before moving forward to a phase III confirmatory trial. A correct dose is one that is actually better than control. A popular model in phase II is an independent model that puts no structure on the dose-response relationship. Unfortunately, the independent model does not efficiently use information from related doses. One very successful alternate model improves power using a pre-specified dose-response structure. Past research indicates that EMAX models are broadly successful and therefore attractive for designing dose-response trials. However, there may be instances of slight risk of nonmonotone trends that need to be addressed when planning a clinical trial design. We propose to add hierarchical parameters to the EMAX model. The added layer allows information about the treatment effect in one dose to be “borrowed” when estimating the treatment effect in another dose. This is referred to as the hierarchical EMAX model. Our paper compares three different models (independent, EMAX, and hierarchical EMAX) and two different design strategies. The first design considered is Bayesian with a fixed trial design, and it has a fixed schedule for randomization. The second design is Bayesian but adaptive, and it uses response adaptive randomization. In this article, a randomized trial of patients with severe traumatic brain injury is provided as a motivating example.

Original languageEnglish (US)
JournalStatistics in Medicine
DOIs
StatePublished - Jan 1 2019
Externally publishedYes

Fingerprint

Bayesian Hierarchical Model
Dose-response
Random Allocation
Clinical Trials
Efficacy
Dose
Appointments and Schedules
Treatment Effects
Randomisation
Therapeutics
Research
Model
Randomized Trial
Hierarchical Model
Alternate
Schedule
Planning
Design
Traumatic Brain Injury

Keywords

  • dosing design, Bayesian models
  • EMAX
  • hierarchical models
  • logistic

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Gajewski, B. J., Meinzer, C., Berry, S. M., Rockswold, G. L., Barsan, W. G., Korley, F., & Martin, R. H. (2019). Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials. Statistics in Medicine. https://doi.org/10.1002/sim.8167

Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials. / Gajewski, Byron J.; Meinzer, Caitlyn; Berry, Scott M.; Rockswold, Gaylan L.; Barsan, William G.; Korley, Frederick; Martin, Renee H.

In: Statistics in Medicine, 01.01.2019.

Research output: Contribution to journalArticle

Gajewski, Byron J. ; Meinzer, Caitlyn ; Berry, Scott M. ; Rockswold, Gaylan L. ; Barsan, William G. ; Korley, Frederick ; Martin, Renee H. / Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials. In: Statistics in Medicine. 2019.
@article{519dc780566e498cb0808441395109a7,
title = "Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials",
abstract = "A primary goal of a phase II dose-ranging trial is to identify a correct dose before moving forward to a phase III confirmatory trial. A correct dose is one that is actually better than control. A popular model in phase II is an independent model that puts no structure on the dose-response relationship. Unfortunately, the independent model does not efficiently use information from related doses. One very successful alternate model improves power using a pre-specified dose-response structure. Past research indicates that EMAX models are broadly successful and therefore attractive for designing dose-response trials. However, there may be instances of slight risk of nonmonotone trends that need to be addressed when planning a clinical trial design. We propose to add hierarchical parameters to the EMAX model. The added layer allows information about the treatment effect in one dose to be “borrowed” when estimating the treatment effect in another dose. This is referred to as the hierarchical EMAX model. Our paper compares three different models (independent, EMAX, and hierarchical EMAX) and two different design strategies. The first design considered is Bayesian with a fixed trial design, and it has a fixed schedule for randomization. The second design is Bayesian but adaptive, and it uses response adaptive randomization. In this article, a randomized trial of patients with severe traumatic brain injury is provided as a motivating example.",
keywords = "dosing design, Bayesian models, EMAX, hierarchical models, logistic",
author = "Gajewski, {Byron J.} and Caitlyn Meinzer and Berry, {Scott M.} and Rockswold, {Gaylan L.} and Barsan, {William G.} and Frederick Korley and Martin, {Renee H.}",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/sim.8167",
language = "English (US)",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Bayesian hierarchical EMAX model for dose-response in early phase efficacy clinical trials

AU - Gajewski, Byron J.

AU - Meinzer, Caitlyn

AU - Berry, Scott M.

AU - Rockswold, Gaylan L.

AU - Barsan, William G.

AU - Korley, Frederick

AU - Martin, Renee H.

PY - 2019/1/1

Y1 - 2019/1/1

N2 - A primary goal of a phase II dose-ranging trial is to identify a correct dose before moving forward to a phase III confirmatory trial. A correct dose is one that is actually better than control. A popular model in phase II is an independent model that puts no structure on the dose-response relationship. Unfortunately, the independent model does not efficiently use information from related doses. One very successful alternate model improves power using a pre-specified dose-response structure. Past research indicates that EMAX models are broadly successful and therefore attractive for designing dose-response trials. However, there may be instances of slight risk of nonmonotone trends that need to be addressed when planning a clinical trial design. We propose to add hierarchical parameters to the EMAX model. The added layer allows information about the treatment effect in one dose to be “borrowed” when estimating the treatment effect in another dose. This is referred to as the hierarchical EMAX model. Our paper compares three different models (independent, EMAX, and hierarchical EMAX) and two different design strategies. The first design considered is Bayesian with a fixed trial design, and it has a fixed schedule for randomization. The second design is Bayesian but adaptive, and it uses response adaptive randomization. In this article, a randomized trial of patients with severe traumatic brain injury is provided as a motivating example.

AB - A primary goal of a phase II dose-ranging trial is to identify a correct dose before moving forward to a phase III confirmatory trial. A correct dose is one that is actually better than control. A popular model in phase II is an independent model that puts no structure on the dose-response relationship. Unfortunately, the independent model does not efficiently use information from related doses. One very successful alternate model improves power using a pre-specified dose-response structure. Past research indicates that EMAX models are broadly successful and therefore attractive for designing dose-response trials. However, there may be instances of slight risk of nonmonotone trends that need to be addressed when planning a clinical trial design. We propose to add hierarchical parameters to the EMAX model. The added layer allows information about the treatment effect in one dose to be “borrowed” when estimating the treatment effect in another dose. This is referred to as the hierarchical EMAX model. Our paper compares three different models (independent, EMAX, and hierarchical EMAX) and two different design strategies. The first design considered is Bayesian with a fixed trial design, and it has a fixed schedule for randomization. The second design is Bayesian but adaptive, and it uses response adaptive randomization. In this article, a randomized trial of patients with severe traumatic brain injury is provided as a motivating example.

KW - dosing design, Bayesian models

KW - EMAX

KW - hierarchical models

KW - logistic

UR - http://www.scopus.com/inward/record.url?scp=85065652949&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85065652949&partnerID=8YFLogxK

U2 - 10.1002/sim.8167

DO - 10.1002/sim.8167

M3 - Article

C2 - 31070807

AN - SCOPUS:85065652949

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

ER -