Xiaodong Luo1, Bo Huang2, Hui Quan1. 1. Department of Biostatistics and Programming, Research and Development, Sanofi U.S., Bridgewater, NJ, USA. 2. Pfizer Inc., New London, CT, USA.
Abstract
BACKGROUND/AIMS: Restricted mean survival time has become a popular treatment effect measurement because of its nice interpretability. However, study design based on restricted mean survival times often requires extensive simulation studies as the variance structure is hard to obtain analytically. This article aims to provide a flexible approach to conduct study design and monitoring based on the restricted mean survival times without resorting to simulation. METHODS: We assume that both the event time and censoring time distributions are piecewise exponential, and the accrual distribution is piecewise uniform, with which the restricted mean survival times and their variance-covariance structure can be conveniently computed. RESULTS: Since we allow arbitrary number of pieces in the piecewise exponential and uniform distributions, the resulting model can handle a wide range of scenarios. The usefulness of the approach is demonstrated via an example. CONCLUSION: The proposed approach is flexible and useful in the design and monitoring of survival trials based on restricted mean survival times.
BACKGROUND/AIMS: Restricted mean survival time has become a popular treatment effect measurement because of its nice interpretability. However, study design based on restricted mean survival times often requires extensive simulation studies as the variance structure is hard to obtain analytically. This article aims to provide a flexible approach to conduct study design and monitoring based on the restricted mean survival times without resorting to simulation. METHODS: We assume that both the event time and censoring time distributions are piecewise exponential, and the accrual distribution is piecewise uniform, with which the restricted mean survival times and their variance-covariance structure can be conveniently computed. RESULTS: Since we allow arbitrary number of pieces in the piecewise exponential and uniform distributions, the resulting model can handle a wide range of scenarios. The usefulness of the approach is demonstrated via an example. CONCLUSION: The proposed approach is flexible and useful in the design and monitoring of survival trials based on restricted mean survival times.
Keywords:
Restricted mean survival times; design and monitoring; non-uniform accrual; piecewise exponential; survival trials