Transduction of Semi-supervised Regression Targets in Survival Analysis for Medical Prognosis

A crucial challenge in predictive modeling for survival analysis applications such as medical prognosis is the accounting of censored observations in the data. While these time-to-event predictions inherently represent a regression problem, traditional regression approaches are challenged by the censored characteristics of the data. In such problems the true target times of a majority of instances are unknown, what is known is a censored target representing some indeterminate time before the true target time. While censored samples can be considered as semi-supervised targets, the current limited efforts in semi-supervised regression do not take into account the partial nature of unsupervised information, samples are treated as either fully labeled or unlabelled. In this work we present a novel approach towards modifying an existing state-of-the-art survival analysis method by incorporating semi-supervised learning. The true target times are approximated from the censored times through transduction to improve predictive performance. Our proposed approach represents one of the first applications of semi-supervised regression to survival analysis and yields a significant improvement in performance over the state-of-the-art in prostate and breast cancer prognosis applications.