|
Abstract:
|
A lack of understanding of human biology creates a hurdle for the development of precision medicines. To overcome this hurdle we need to better understand the potential synergy between a given treatment (vs. placebo or active control) and various demographic or genetic factors, disease history and severity, etc., with the goal of identifying those patients at increased risk of exhibiting meaningful treatment benefit. For this reason we proposed the VG method, which combines the idea of individual treatment effect (ITE) from the Virtual Twins method (Foster et al 2013, Stat Med) and the unbiased variable selection and cutoff value determination algorithm from the GUIDE method (Loh 2015, Stat Med). Simulation results showed the VG method to have less variable selection bias than Virtual Twins and higher statistical power than GUIDE in the presence of prognostic variables with strong treatment effects. The type I error and predictive performance of Virtual Twins, GUIDE and VG were also compared through the use of simulation studies and a randomized clinical trial for Alzheimer's disease.
|
