FSGLmstate is an R package that performs variable selection via fused sparse-group lasso (FSGL) penalized multi-state models (Miah et al., 2024).
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. We integrate this approach to data-driven variable selection by extended regularization methods within multi-state model building. We propose the fused sparse-group lasso (FSGL) penalized Cox-type regression in the framework of multi-state models combining the penalization concepts of pairwise differences of covariate effects along with transition-wise grouping. For optimization, we adapt the alternating direction method of multipliers (ADMM) algorithm to Cox-type hazards regression in the multi-state setting. In a simulation study and application to acute myeloid leukemia (AML) data, we evaluate the algorithm's ability to select a sparse model incorporating relevant transition-specific effects and similar cross-transition effects. We investigate settings in which the combined penalty is beneficial compared to global lasso regularization.
You can install the development package version FSGLmstate from GitHub with:
# install.packages("devtools")
devtools::install_github("k-miah/FSGLmstate")Load the package in R with:
library(FSGLmstate)penalty_matrix_K(): Generation of a penalty structure matrix for use in penalized regression incorporating lasso, fused and group-lasso penaltiesfit.admm.fsgl.mstate(): Alternating direction method of multipliers (ADMM) optimization for FSGL penalized multi-state models for fixed set of tuning parametersgcv.fit.admm.fsgl.mstate(): Alternating direction method of multipliers (ADMM) optimization for FSGL penalized multi-state models for optimal tuning parameters via generalized cross-validation (GCV) selection criterion
Bugs and issues can be reported at https://github.com/k-miah/FSGLmstate/issues.
For any questions or feedback, please reach out to k.miah@dkfz.de.