Bayesian randomized clinical trials: A decision-theoretic sequential design

The authors propose a Bayesian decision-theoretic framework justifying randomization in clinical trials. Noting that the decision maker is often unable or unwilling to specify a unique utility function, they develop a sequential myopic design that includes randomization justified by the consideratio...

Full description

Saved in:
Bibliographic Details
Published in:Canadian journal of statistics 2004-12, Vol.32 (4), p.387-402
Main Authors: Christen, J.Andres, MÜLLER, Peter, Wathen, Kyle, Wolf, Judith
Format: Article
Language:English
Subjects:
Algorithms
Backward induction
Bayesian analysis
Bayesian method
Cancer
Clinical trials
Dosage
Drug dosages
Expected utility
Experimentation
Interferon
Introns
Mathematical analysis
Medical research
Ovarian cancer
Probabilities
Random allocation
robustness
Standards of care
Statistical methods
Studies
Utility functions
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The authors propose a Bayesian decision-theoretic framework justifying randomization in clinical trials. Noting that the decision maker is often unable or unwilling to specify a unique utility function, they develop a sequential myopic design that includes randomization justified by the consideration of a set of utility functions. Randomization is introduced over all nondominated treatments, allowing for interim removal of treatments and early stopping. The authors illustrate their approach in the context of a study to find the optimal dose of pegylated interferon for platinum resistant ovarian cancer. They also develop an algorithm to implement their methodology in a phase II clinical trial comparing several competing experimental treatments. /// Les auteurs proposent un cadre décisionnel bayésien permettant de justifier la pratique de la randomisation dans les essais cliniques. Partant du constat que le décideur est souvent incapable ou non désireux de préciser sa fonction d'utilité, ils développent un plan séquentiel myopique dans lequel la randomisation découle de la considération de plusieurs fonctions d'utilité. L'introduction de la randomisation sur l'ensemble des traitements non dominés permet de légitimer le retrait intérimaire de traitements et la clôture hâtive des essais. Les auteurs illustrent leur approche dans le contexte d'une étude visant à identifier la dose optimale d'interféron péguylé dans les cas de cancer ovarien platino-résistant. Ils développent aussi un algorithme permettant d'implanter leur méthodologie dans un essai clinique de phase II visant à comparer plusieurs traitements expérimentaux concurrents.
ISSN:0319-5724
1708-945X
DOI:10.2307/3316023