Variational Deep Survival Machines: Survival Regression with Censored Outcomes
This work addresses survival prediction in domains like healthcare, offering an incremental improvement over existing methods for handling censored data.
The paper tackles survival regression with censored outcomes by proposing a novel method that uses variational auto-encoders to cluster input covariates and combine primitive distributions, achieving competitive scores on datasets SUPPORT and FLCHAIN and demonstrating superior long-term prediction results.
Survival regression aims to predict the time when an event of interest will take place, typically a death or a failure. A fully parametric method [18] is proposed to estimate the survival function as a mixture of individual parametric distributions in the presence of censoring. In this paper, We present a novel method to predict the survival time by better clustering the survival data and combine primitive distributions. We propose two variants of variational auto-encoder (VAE), discrete and continuous, to generate the latent variables for clustering input covariates. The model is trained end to end by jointly optimizing the VAE loss and regression loss. Thorough experiments on dataset SUPPORT and FLCHAIN show that our method can effectively improve the clustering result and reach competitive scores with previous methods. We demonstrate the superior result of our model prediction in the long-term. Our code is available at https://github.com/qinzzz/auton-survival-785.