Reinterpreting survival analysis in the universal approximator age
It addresses the problem of integrating deep learning into survival analysis for researchers and practitioners, offering incremental improvements with technical tools.
The paper tackles the underutilization of deep learning in survival analysis by providing new tools, including a loss function, evaluation metrics, and a universal approximating network that produces survival curves without numeric integration, and shows these outperform other approaches in a large numerical study.
Survival analysis is an integral part of the statistical toolbox. However, while most domains of classical statistics have embraced deep learning, survival analysis only recently gained some minor attention from the deep learning community. This recent development is likely in part motivated by the COVID-19 pandemic. We aim to provide the tools needed to fully harness the potential of survival analysis in deep learning. On the one hand, we discuss how survival analysis connects to classification and regression. On the other hand, we provide technical tools. We provide a new loss function, evaluation metrics, and the first universal approximating network that provably produces survival curves without numeric integration. We show that the loss function and model outperform other approaches using a large numerical study.