1525-1438/asset/IJG_left.gif?v=1&s=d7d2630de02e0bacca2bee82c008dee583d5a6e7)
1525-1438/asset/IJG_centre.gif?v=1&s=d358a70e77526e2636ee90a9a0077527085de8e5)
1525-1438/asset/IJG_right.gif?v=1&s=824f501dff34c5bc22d36fa4aedace1f87078a08)
Practical model-based dose-finding in phase I clinical trials: Methods based on toxicity
Article first published online: 13 JUN 2003
DOI: 10.1046/j.1525-1438.2003.13202.x
Additional Information
How to Cite
Thall, P. F. and Lee, S.-J. (2003), Practical model-based dose-finding in phase I clinical trials: Methods based on toxicity. International Journal of Gynecological Cancer, 13: 251–261. doi: 10.1046/j.1525-1438.2003.13202.x
Publication History
- Issue published online: 13 JUN 2003
- Article first published online: 13 JUN 2003
- Accepted for publication March 3, 2003.
- Abstract
- Article
- References
- Cited By
Keywords:
- adaptive decision making;
- Bayesian inference;
- clinical trial;
- dose-finding;
- phase I;
- safety monitoring;
- toxicity
Abstract.
We describe two practical, outcome-adaptive statistical methods for dose-finding in phase I clinical trials. One is the continual reassessment method and the other is based on a logistic regression model. Both methods use Bayesian probability models as a basis for learning from the accruing data during the trial, choosing doses for successive patient cohorts, and selecting a maximum tolerable dose (MTD). These methods are illustrated and compared to the conventional 3+3 algorithm by application to a particular trial in renal cell carcinoma. We also compare their average behavior by computer simulation under each of several hypothetical dose-toxicity curves. The comparisons show that the Bayesian methods are much more reliable than the conventional algorithm for selecting an MTD, and that they have a low risk of treating patients at unacceptably toxic doses.