Deep Survival Machines: Fully Parametric Survival Regression and Representation Learning for Censored Data with Competing Risks

• Main Authors: Dubrawski, A. (Author), Li, X. (Author), Nagpal, C. (Author)
• Format: Article
• Language: English
• Published: Institute of Electrical and Electronics Engineers Inc. 2021
• Subjects: article; bioinformatics; censored regression; Competing risks; controlled study; Cox proportional hazard model; deep learning; Deep learning; graphical models; Hazards; human; Humans; mixture of experts; Models, Statistical; New approaches; Parameter estimation; Parametric estimation; prediction; proportional hazards model; Proportional Hazards Models; Real-world datasets; Relative risks; remission; risk; Risk; risk assessment; risk factor; Risk perception; statistical model; survival analysis; Survival analysis; Survival Analysis; Survival distributions; survival time; Time to events
• Online Access: View Fulltext in Publisher

 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 hazards 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. © 2013 IEEE.