Metaparametric Neural Networks for Survival Analysis

TL;DR

This paper introduces a metaparametric neural network framework for survival analysis that overcomes limitations of existing models by enabling flexible, structure-agnostic estimation of time-to-event functions, improving accuracy on real-world data.

Contribution

The paper proposes a novel metaparametric neural network framework that generalizes and extends existing survival analysis methods, allowing for flexible, unrestricted function estimation.

Findings

Outperforms state-of-the-art methods in capturing nonlinearities.

Effectively identifies temporal patterns in survival data.

Achieves more accurate survival estimations on real-world datasets.

Abstract

Survival analysis is a critical tool for the modelling of time-to-event data, such as life expectancy after a cancer diagnosis or optimal maintenance scheduling for complex machinery. However, current neural network models provide an imperfect solution for survival analysis as they either restrict the shape of the target probability distribution or restrict the estimation to pre-determined times. As a consequence, current survival neural networks lack the ability to estimate a generic function without prior knowledge of its structure. In this article, we present the metaparametric neural network framework that encompasses existing survival analysis methods and enables their extension to solve the aforementioned issues. This framework allows survival neural networks to satisfy the same independence of generic function estimation from the underlying data structure that characterizes their regression and classification counterparts. Further, we demonstrate the application of the metaparametric framework using both simulated and large real-world datasets and show that it outperforms the current state-of-the-art methods in (i) capturing nonlinearities, and (ii) identifying temporal patterns, leading to more accurate overall estimations whilst placing no restrictions on the underlying function structure.