Highly censored survival analysis via data augmentation

Abstract

Recently, survival models have found vast applications in biostatistics, bioinformatics, reliability engineering, finance and related fields. But survival data often face the small sample size and highly censored problem due to long experimental periods and high data collection costs. The lack of sufficient samples severely hinders the predictive power of survival models, especially when data-driven machine learning methods are increasingly used in survival analysis. In this research, we propose two survival data augmentation algorithms, namely Parametric algorithm for Survival Data Augmentation via a Two-stage process (PSDATA) and non-Parametric algorithm for Survival Data Augmentation via a Two-stage process(nPSDATA), which can effectively expand the small sample survival data set. We validate the effectiveness of the algorithms on both simulated and real data sets based on RSF and Cox models. Extensive experiments have shown that both strategies can improve the predictive performance substantially. Further experiments have revealed that using the proposed approaches, the cost of data collection can be reduced by a large extent with only a slight decrease in predictability.