DECISION-MAKING DURING A PHASE-III RANDOMIZED CONTROLLED TRIAL

Experiments such as clinical trials should be carried out with specifi c objectives. For example, in a trial designed to prevent disease, spe cific considerations should be made concerning the impact of the trial on the health of the target population, including the participants in the trial. These objectives should be assessed continually in light o f data accumulating from the trial. Accumulating evidence should be ju dged in the context of changing circumstances external to the trial, a nd the trial's design possibly modified. An important type of modifica tion is stopping the trial. This is a sequential decision problem that can be addressed using a Bayesian approach and the methods of dynamic programming. As an example we consider a vaccine trial for the preven tion of haemophilus influenzae type b. The objective we consider is mi nimizing the number of cases of this disease in a Native American popu lation over a specified horizon. We assess the prior probability distr ibution of vaccine efficacy. We also assess the probability of regulat ory approval for widespread use of the vaccine, depending on the data presented to the regulatory officials. In deciding whether to continue the trial we weigh the impact of the possible future results by their (predictive) probabilities. We address the sensitivity of the optimal stopping policy to the prior probability distribution, to the assesse d probability of regulatory approval, and to the horizon.