Time-to-Event Prediction with Neural Networks and Cox Regression
This work addresses time-to-event prediction for applications like survival analysis, offering incremental improvements by combining neural networks with established Cox regression methods.
The paper tackles time-to-event prediction by extending the Cox proportional hazards model with neural networks, proposing a scalable loss function that approximates the Cox partial log-likelihood and yields competitive performance, typically achieving the best Brier score and binomial log-likelihood on real-world datasets.
New methods for time-to-event prediction are proposed by extending the Cox proportional hazards model with neural networks. Building on methodology from nested case-control studies, we propose a loss function that scales well to large data sets, and enables fitting of both proportional and non-proportional extensions of the Cox model. Through simulation studies, the proposed loss function is verified to be a good approximation for the Cox partial log-likelihood. The proposed methodology is compared to existing methodologies on real-world data sets, and is found to be highly competitive, typically yielding the best performance in terms of Brier score and binomial log-likelihood. A python package for the proposed methods is available at https://github.com/havakv/pycox.