FastCPH: Efficient Survival Analysis for Neural Networks
This addresses the need for efficient and accurate survival prediction in clinical or genetic settings, though it is incremental as it builds on prior neural network methods.
The paper tackles the problem of inefficient and numerically incorrect neural network extensions of the Cox proportional hazards model for survival analysis, resulting in FastCPH, a method that runs in linear time and outperforms existing approaches.
The Cox proportional hazards model is a canonical method in survival analysis for prediction of the life expectancy of a patient given clinical or genetic covariates -- it is a linear model in its original form. In recent years, several methods have been proposed to generalize the Cox model to neural networks, but none of these are both numerically correct and computationally efficient. We propose FastCPH, a new method that runs in linear time and supports both the standard Breslow and Efron methods for tied events. We also demonstrate the performance of FastCPH combined with LassoNet, a neural network that provides interpretability through feature sparsity, on survival datasets. The final procedure is efficient, selects useful covariates and outperforms existing CoxPH approaches.