Deep Clustering Survival Machines with Interpretable Expert Distributions

TL;DR

This paper introduces deep clustering survival machines, a hybrid model that combines discriminative and generative approaches to improve heterogeneity characterization and interpretability in survival analysis.

Contribution

It proposes a novel hybrid survival analysis method that models survival data with a mixture of expert distributions and learns instance-specific weights discriminatively.

Findings

Achieves promising clustering results on real and synthetic data

Provides competitive time-to-event prediction performance

Enables interpretable subgrouping based on expert distributions

Abstract

Conventional survival analysis methods are typically ineffective to characterize heterogeneity in the population while such information can be used to assist predictive modeling. In this study, we propose a hybrid survival analysis method, referred to as deep clustering survival machines, that combines the discriminative and generative mechanisms. Similar to the mixture models, we assume that the timing information of survival data is generatively described by a mixture of certain numbers of parametric distributions, i.e., expert distributions. We learn weights of the expert distributions for individual instances according to their features discriminatively such that each instance's survival information can be characterized by a weighted combination of the learned constant expert distributions. This method also facilitates interpretable subgrouping/clustering of all instances according to their associated expert distributions. Extensive experiments on both real and synthetic datasets have demonstrated that the method is capable of obtaining promising clustering results and competitive time-to-event predicting performance.