Preview

PDF, English Download (1MB) | Terms of use

Abstract

In multi-state models based on high-dimensional data, effective modeling strategies are required to determine an optimal, ideally parsimonious model. In particular, linking covariate effects across transitions is needed to conduct joint variable selection. A useful technique to reduce model complexity is to address homogeneous covariate effects for distinct transitions. This approach is integrated to data-driven variable selection by extended regularization methods within multi-state model building. The fused sparse-group lasso (FSGL) penalized Cox-type regression is proposed in the framework of multi-state models combining the penalization concepts of pairwise differences of covariate effects along with transition-wise grouping. For optimization, the alternating direction method of multipliers (ADMM) algorithm is adapted to transition-specific hazards regression in the multi-state setting. In a simulation study and application to acute myeloid leukemia (AML) data, the algorithm’s ability to select a sparse model incorporating relevant transition-specific effects and similar cross-transition effects is evaluated. Settings in which the combined penalty is beneficial compared to global lasso regularization are investigated.