The Randomized CRM

An Approach to Overcoming the Long-Memory Property of the CRM

Research output: Contribution to journalArticle

Abstract

The primary object of a Phase I clinical trial is to determine the maximum tolerated dose (MTD). Typically, the MTD is identified using a dose-escalation study, where initial subjects are treated at the lowest dose level and subsequent subjects are treated at progressively higher dose levels until the MTD is identified. The continual reassessment method (CRM) is a popular model-based dose-escalation design, which utilizes a formal model for the relationship between dose and toxicity to guide dose finding. Recently, it was shown that the CRM has a tendency to get “stuck” on a dose level, with little escalation or de-escalation in the late stages of the trial, due to the long-memory property of the CRM. We propose the randomized CRM (rCRM), which introduces random escalation and de-escalation into the standard CRM dose-finding algorithm, as well as a hybrid approach that incorporates escalation and de-escalation only when certain criteria are met. Our simulation results show that both the rCRM and the hybrid approach reduce the trial-to-trial variability in the number of cohorts treated at the MTD but that the hybrid approach has a more favorable tradeoff with respect to the average number treated at the MTD.

Original languageEnglish (US)
Pages (from-to)1028-1042
Number of pages15
JournalJournal of Biopharmaceutical Statistics
Volume27
Issue number6
DOIs
StatePublished - Nov 2 2017

Fingerprint

Continual Reassessment Method
Maximum Tolerated Dose
Long Memory
Dose
Hybrid Approach
Dose Finding
Clinical Trials, Phase I
Phase I Trial
Formal Model
Toxicity
Clinical Trials
Lowest
Trade-offs
Model-based

Cite this

The Randomized CRM : An Approach to Overcoming the Long-Memory Property of the CRM. / Koopmeiners, Joseph S.; Wey, Andrew.

In: Journal of Biopharmaceutical Statistics, Vol. 27, No. 6, 02.11.2017, p. 1028-1042.

Research output: Contribution to journalArticle

@article{239e36c5137d43d68aae48d4f24c9605,
title = "The Randomized CRM: An Approach to Overcoming the Long-Memory Property of the CRM",
abstract = "The primary object of a Phase I clinical trial is to determine the maximum tolerated dose (MTD). Typically, the MTD is identified using a dose-escalation study, where initial subjects are treated at the lowest dose level and subsequent subjects are treated at progressively higher dose levels until the MTD is identified. The continual reassessment method (CRM) is a popular model-based dose-escalation design, which utilizes a formal model for the relationship between dose and toxicity to guide dose finding. Recently, it was shown that the CRM has a tendency to get “stuck” on a dose level, with little escalation or de-escalation in the late stages of the trial, due to the long-memory property of the CRM. We propose the randomized CRM (rCRM), which introduces random escalation and de-escalation into the standard CRM dose-finding algorithm, as well as a hybrid approach that incorporates escalation and de-escalation only when certain criteria are met. Our simulation results show that both the rCRM and the hybrid approach reduce the trial-to-trial variability in the number of cohorts treated at the MTD but that the hybrid approach has a more favorable tradeoff with respect to the average number treated at the MTD.",
author = "Koopmeiners, {Joseph S.} and Andrew Wey",
year = "2017",
month = "11",
day = "2",
doi = "10.1080/10543406.2017.1293076",
language = "English (US)",
volume = "27",
pages = "1028--1042",
journal = "Journal of Biopharmaceutical Statistics",
issn = "1054-3406",
publisher = "Taylor and Francis Ltd.",
number = "6",

}

TY - JOUR

T1 - The Randomized CRM

T2 - An Approach to Overcoming the Long-Memory Property of the CRM

AU - Koopmeiners, Joseph S.

AU - Wey, Andrew

PY - 2017/11/2

Y1 - 2017/11/2

N2 - The primary object of a Phase I clinical trial is to determine the maximum tolerated dose (MTD). Typically, the MTD is identified using a dose-escalation study, where initial subjects are treated at the lowest dose level and subsequent subjects are treated at progressively higher dose levels until the MTD is identified. The continual reassessment method (CRM) is a popular model-based dose-escalation design, which utilizes a formal model for the relationship between dose and toxicity to guide dose finding. Recently, it was shown that the CRM has a tendency to get “stuck” on a dose level, with little escalation or de-escalation in the late stages of the trial, due to the long-memory property of the CRM. We propose the randomized CRM (rCRM), which introduces random escalation and de-escalation into the standard CRM dose-finding algorithm, as well as a hybrid approach that incorporates escalation and de-escalation only when certain criteria are met. Our simulation results show that both the rCRM and the hybrid approach reduce the trial-to-trial variability in the number of cohorts treated at the MTD but that the hybrid approach has a more favorable tradeoff with respect to the average number treated at the MTD.

AB - The primary object of a Phase I clinical trial is to determine the maximum tolerated dose (MTD). Typically, the MTD is identified using a dose-escalation study, where initial subjects are treated at the lowest dose level and subsequent subjects are treated at progressively higher dose levels until the MTD is identified. The continual reassessment method (CRM) is a popular model-based dose-escalation design, which utilizes a formal model for the relationship between dose and toxicity to guide dose finding. Recently, it was shown that the CRM has a tendency to get “stuck” on a dose level, with little escalation or de-escalation in the late stages of the trial, due to the long-memory property of the CRM. We propose the randomized CRM (rCRM), which introduces random escalation and de-escalation into the standard CRM dose-finding algorithm, as well as a hybrid approach that incorporates escalation and de-escalation only when certain criteria are met. Our simulation results show that both the rCRM and the hybrid approach reduce the trial-to-trial variability in the number of cohorts treated at the MTD but that the hybrid approach has a more favorable tradeoff with respect to the average number treated at the MTD.

UR - http://www.scopus.com/inward/record.url?scp=85016064780&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016064780&partnerID=8YFLogxK

U2 - 10.1080/10543406.2017.1293076

DO - 10.1080/10543406.2017.1293076

M3 - Article

VL - 27

SP - 1028

EP - 1042

JO - Journal of Biopharmaceutical Statistics

JF - Journal of Biopharmaceutical Statistics

SN - 1054-3406

IS - 6

ER -