|
Abstract:
|
In the treatment of chronic diseases and disorders, an apparent lack of early efficacy may lead to discontinuation of treatment. It is important to determine whether a desired early outcome corresponds to a beneficial long-term effect of continuing treatment, and conversely, whether the absence of such an outcome corresponds to a lack of long-term benefit. However, clinical trials of such treatments are not commonly designed to answer such questions, for example by randomizing subjects to continue or discontinue treatment after observing early outcomes. We propose an approach to estimating the effect of continuing treatment after observing early outcomes using data from randomized controlled trials in which treatment discontinuation was not part of the design. Our approach estimates average causal effects of continuing treatment on long-term outcomes in principal strata defined by the potential early outcomes under treatment. We use our approach to estimate the effects of continuing to take gaboxadol to treat primary insomnia conditional on early improvement (or lack thereof) in subjective sleep quality after two nights, based on a standard parallel-arm randomized controlled trial.
|
