One key aim of Phase I cancer studies is to identify the dose of a treatment to be further evaluated in Phase II. We describe, in non-statistical language, three classes of dose-escalation trial design and compare their properties.
We review three classes of dose-escalation design suitable for Phase I cancer trials: algorithmic approaches (including the popular 3 + 3 design), Bayesian model-based designs and Bayesian curve-free methods. We describe an example from each class and summarize the advantages and disadvantages of the design classes.
The main benefit of algorithmic approaches is the simplicity with which they may be communicated: it may be for this reason alone that they are still employed in the vast majority of Phase I trials. Model-based and curve-free Bayesian approaches are preferable to algorithmic methods due to their superior ability to identify the dose with the desired toxicity rate and their allocation of a greater proportion of patients to doses at, or close to, that dose.
For statistical and practical reasons, algorithmic methods cannot be recommended. The choice between a Bayesian model-based or curve-free approach depends on the previous information available about the compound under investigation. If this provides assurance about a particular model form, the model-based approach would be appropriate; if not, the curve-free method would be preferable.