Dose-Finding Designs Based on the Continual Reassessment Method

Authored by: John O’Quigley , Alexia Iasonos

Handbook of Statistics in Clinical Oncology

Print publication date:  March  2012
Online publication date:  March  2012

Print ISBN: 9781439862001
eBook ISBN: 9781439862018
Adobe ISBN:


 Download Chapter



This review describes the basic ideas behind the continual reassessment method (CRM), as it is used in Phase I and Phase I/II dose finding. We recall some important technical considerations, some key properties of the method, and the possibility for substantial generalization, specifically, the use of graded information on toxicities, the incorporation of a stopping rule leading to potential reductions in sample size, the incorporation of information on patient heterogeneity, the incorporation of pharmacokinetics, and the possibility of modeling in the presence of drug combinations. In its most classical setting the CRM is used to identify the maximum tolerated dose (MTD) where only information on toxicities is used. For Phase I/II designs, in which information on efficacy can be obtained within a comparable time frame as that on toxicity, we can use the CRM structure, together with the sequential probability ratio test, to construct very effective designs to locate the dose producing the greatest rate of success. We consider more involved CRM designs, for example, designs that account for low-grade toxicities, pharmacokinetic endpoints, patient heterogeneity, partial ordering in drug combinations and model averaging techniques. The theory that backs up this extra complexity comes under the umbrella of Bayesian model choice.

Search for more...
Back to top

Use of cookies on this website

We are using cookies to provide statistics that help us give you the best experience of our site. You can find out more in our Privacy Policy. By continuing to use the site you are agreeing to our use of cookies.