Abstract:
|
A recent focus in the health sciences has been the development of personalized medicine, which includes determining the population for which a given treatment is effective. The credible subgroups approach provides a pair of bounding subgroups for the benefiting subgroup constructed so that it is likely that one contains only patients who benefit and the other contains all patients who benefit, but the method has so far only been developed for linear models. In this paper we develop the details required to follow the credible subgroups approach in more realistic settings by considering semiparametric regression models, conditional power simulations, and improved multiple testing through a step-down procedure. We illustrate our approach using data from four recent trials of Alzheimer's disease treatments.
|