Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks
This work addresses survival analysis for medical or reliability fields by providing a novel method for handling censored data with competing risks, though it appears incremental as it builds on existing parametric and deep learning techniques.
The paper tackled the problem of estimating relative risks in time-to-event prediction with censored data by introducing a fully parametric approach that avoids constant proportional hazard assumptions, demonstrating benefits through experiments on real-world datasets with different censoring levels and showing advantages in competing risks scenarios.
We describe a new approach to estimating relative risks in time-to-event prediction problems with censored data in a fully parametric manner. Our approach does not require making strong assumptions of constant proportional hazard of the underlying survival distribution, as required by the Cox-proportional hazard model. By jointly learning deep nonlinear representations of the input covariates, we demonstrate the benefits of our approach when used to estimate survival risks through extensive experimentation on multiple real world datasets with different levels of censoring. We further demonstrate advantages of our model in the competing risks scenario. To the best of our knowledge, this is the first work involving fully parametric estimation of survival times with competing risks in the presence of censoring.