Neural Fine-Gray: Monotonic Neural Networks for Competing Risks
Abstract
Time-to-event modelling, known as survival analysis, differs from standard regression as it addresses \emph{censoring} in patients who do not experience the event of interest. Despite competitive performances in tackling this problem, machine learning methods often ignore other \emph{competing risks} that preclude the event of interest. This practice biases the survival estimation. Extensions to address this challenge often rely on parametric assumptions or numerical estimations leading to sub-optimal survival approximations. This paper leverages constrained monotonic neural networks to model each competing survival distribution. This modelling choice ensures the exact likelihood maximisation at a reduced computational cost by using automatic differentiation. The effectiveness of the solution is demonstrated on one synthetic and three medical datasets. Finally, we discuss the implications of considering competing risks when developing risk scores for medical practice.
Cite
Text
Jeanselme et al. "Neural Fine-Gray: Monotonic Neural Networks for Competing Risks." Proceedings of the Conference on Health, Inference, and Learning, 2023.Markdown
[Jeanselme et al. "Neural Fine-Gray: Monotonic Neural Networks for Competing Risks." Proceedings of the Conference on Health, Inference, and Learning, 2023.](https://mlanthology.org/chil/2023/jeanselme2023chil-neural/)BibTeX
@inproceedings{jeanselme2023chil-neural,
title = {{Neural Fine-Gray: Monotonic Neural Networks for Competing Risks}},
author = {Jeanselme, Vincent and Yoon, Chang Ho and Tom, Brian and Barrett, Jessica},
booktitle = {Proceedings of the Conference on Health, Inference, and Learning},
year = {2023},
pages = {379-392},
volume = {209},
url = {https://mlanthology.org/chil/2023/jeanselme2023chil-neural/}
}