Wednesday, June 21, 2017
Polo Santa Marta, Via Cantarane 24, Room 1.59
When is it `cost-effective' to stop a sequential clinical trial? Might cost-effectiveness criteria help investigators decide whether or not to conduct a sequential trial, or one of a fixed sample size, at the design stage? What barriers stand in the way of taking new theoretical methodology to application?
We present a Bayesian decision-theoretic model of the optimal stopping of a sequential clinical trial on cost-effectiveness grounds which accounts for: 1. the cost of carrying out research, of treatment and of switching health technologies; 2. benefits accruing to trial participants and the wider study population; 3. delay in observing the primary end point. Dynamic programming yields the optimal policy in (sample size x posterior mean) space, based on a diffusion process approximation, defining upper and lower stopping boundaries for the trial. Monte Carlo simulations show that the policy outperforms alternative, non-sequential, trial designs in terms of the expected benefit of health technology adoption, net of trial costs. But they also show that the expected sample size of the optimal Bayes sequential policy can be greater than, equal to, or less than, that of comparator designs. Why? Because the optimal policy achieves the sample size which appropriately balances the expected benefit to patients with the cost of learning during the trial.
With a particular focus on taking theory to application, we assess the benefits and challenges to deployment of the model to value-based health technology assessment.
Background material may be found in the two main publications from our ongoing collaboration: