Best Intention Designs in Dose–finding Studies

In the dose–finding setting, we discuss and compare adaptive designs, including those which allocate each new patient (or a cohort of patients) to the dose currently viewed as the best one, for example, the seemingly most efficacious. We call this type of allocation “best intention” designs and found that, similar to other areas of life, the best intention may pave the road to rather disastrous situations. Theoretical results originating in research on optimal control strategies suggest that the best intention approach needs modifications to insure convergence to the “best” dose. Monte Carlo simulations provide corroborating evidence that caution is needed. Indeed, even for very simple models, best intention designs may converge to a wrong dose with non–zero probability and in some cases almost for sure. keywords: response-adaptive designs, sequential treatment allocation, clinical trials, optimal design