Survival ensemble with sparse random projections for censored clinical and gene expression data

Abstract

Random projection is a powerful method for dimensionality reduction while its applications in high-dimensional survival analysis is rather limited. In this research, we propose a novel survival ensemble model based on sparse random projection and survival trees. Supported by the proper statistical analysis, we show that the proposed model is comparable to or better than popular survival models such as random survival forest, regularized Cox proportional hazard and fast cocktail models on high-dimensional microarray gene expression right censored data.