Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis

Dominic Danks, Christopher Yau
Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, PMLR 151:7240-7256, 2022.

Abstract

Survival models — particularly those able to account for patient comorbidities via competing risks analysis — offer valuable prognostic information to clinicians making critical decisions and represent a growing area of application for machine learning approaches. However, current methods typically involve restrictive parameterisations, discretisation of time or the modelling of only one event cause. In this paper, we highlight how general cumulative distribution functions can be naturally expressed via neural network-based ordinary differential equations and how this observation can be utilised in survival analysis. In particular, we present DeSurv, a neural derivative-based approach capable of avoiding aforementioned restrictions and flexibly modelling competing-risk survival data in continuous time. We apply DeSurv to both single-risk and competing-risk synthetic and real-world datasets and obtain results which compare favourably with current state-of-the-art models.

Cite this Paper


BibTeX
@InProceedings{pmlr-v151-danks22a, title = { Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis }, author = {Danks, Dominic and Yau, Christopher}, booktitle = {Proceedings of The 25th International Conference on Artificial Intelligence and Statistics}, pages = {7240--7256}, year = {2022}, editor = {Camps-Valls, Gustau and Ruiz, Francisco J. R. and Valera, Isabel}, volume = {151}, series = {Proceedings of Machine Learning Research}, month = {28--30 Mar}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v151/danks22a/danks22a.pdf}, url = {https://proceedings.mlr.press/v151/danks22a.html}, abstract = { Survival models — particularly those able to account for patient comorbidities via competing risks analysis — offer valuable prognostic information to clinicians making critical decisions and represent a growing area of application for machine learning approaches. However, current methods typically involve restrictive parameterisations, discretisation of time or the modelling of only one event cause. In this paper, we highlight how general cumulative distribution functions can be naturally expressed via neural network-based ordinary differential equations and how this observation can be utilised in survival analysis. In particular, we present DeSurv, a neural derivative-based approach capable of avoiding aforementioned restrictions and flexibly modelling competing-risk survival data in continuous time. We apply DeSurv to both single-risk and competing-risk synthetic and real-world datasets and obtain results which compare favourably with current state-of-the-art models. } }
Endnote
%0 Conference Paper %T Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis %A Dominic Danks %A Christopher Yau %B Proceedings of The 25th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2022 %E Gustau Camps-Valls %E Francisco J. R. Ruiz %E Isabel Valera %F pmlr-v151-danks22a %I PMLR %P 7240--7256 %U https://proceedings.mlr.press/v151/danks22a.html %V 151 %X Survival models — particularly those able to account for patient comorbidities via competing risks analysis — offer valuable prognostic information to clinicians making critical decisions and represent a growing area of application for machine learning approaches. However, current methods typically involve restrictive parameterisations, discretisation of time or the modelling of only one event cause. In this paper, we highlight how general cumulative distribution functions can be naturally expressed via neural network-based ordinary differential equations and how this observation can be utilised in survival analysis. In particular, we present DeSurv, a neural derivative-based approach capable of avoiding aforementioned restrictions and flexibly modelling competing-risk survival data in continuous time. We apply DeSurv to both single-risk and competing-risk synthetic and real-world datasets and obtain results which compare favourably with current state-of-the-art models.
APA
Danks, D. & Yau, C.. (2022). Derivative-Based Neural Modelling of Cumulative Distribution Functions for Survival Analysis . Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 151:7240-7256 Available from https://proceedings.mlr.press/v151/danks22a.html.

Related Material