JSM 2014 Home
Online Program Home
My Program

Abstract Details

Activity Number: 636
Type: Topic Contributed
Date/Time: Thursday, August 7, 2014 : 10:30 AM to 12:20 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #313584
Title: Evaluation of Bayesian Logistic Regression Model and 3+3 in a Dose Escalation Study for Combination Drugs: A Simulation Study
Author(s): Muhtarjan Osman*+ and Yijing Shen and Vlad Dragalin
Companies: Onyx Pharmaceuticals and Genentech and Aptiv Solutions
Keywords: dose escalation ; phase I ; continual reassessment method ; simulation ; Bayesian logistic regression model ; target interval
Abstract:

The continual reassessment method based on 2-parameter Bayesian logistic regression model (BLRM) with toxicity target intervals has emerged in recent years as a popular alternative to the standard 3+3 design in oncology dose escalation trials. We assess via simulations the operating characteristics of BLRM, as compared to the conventional 3+3 method, for a dose-escalation study designed to determine the maximum tolerated dose (MTD) of two combination agents. The dose escalation of an investigational drug (Agent2) will be initiated in combination with full dose of a marketed drug (Agent1). The BLRM will continue to assign subjects to the subsequent dose levels of Agent1 until a MTD (MTD1) is reached. After reaching the MTD1, the combination of next higher dose of Agent2 with the lower dose of Agent1 will be tested using BLRM. We summarized the accuracy in identifying the correct MTD, the proportion of subjects experiencing toxicities, and sample sizes across various scenarios. The Bayesian design consistently results in more accurate estimates of the MTD, and treats more subjects at the true MTD level than the 3+3 method.


Authors who are presenting talks have a * after their name.

Back to the full JSM 2014 program




2014 JSM Online Program Home

For information, contact jsm@amstat.org or phone (888) 231-3473.

If you have questions about the Professional Development program, please contact the Education Department.

The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.

ASA Meetings Department  •  732 North Washington Street, Alexandria, VA 22314  •  (703) 684-1221  •  meetings@amstat.org
Copyright © American Statistical Association.