EsmamDS: A more diverse exceptional survival model mining approach

TL;DR

EsmamDS is a novel pattern mining approach that identifies diverse local survival patterns, offering more detailed subgroup characterizations compared to traditional global predictive models.

Contribution

It introduces the EsmamDS algorithm, enhancing diversity and informativeness in discovering local survival patterns with unusual Kaplan-Meier estimates.

Findings

Provides diverse subgroup characterizations of survival behavior.

Addresses pattern redundancy to improve pattern informativeness.

Builds on existing Esmam algorithm for enhanced local pattern discovery.

Abstract

A variety of works in the literature strive to uncover the factors associated with survival behaviour. However, the computational tools to provide such information are global models designed to predict if or when a (survival) event will occur. When approaching the problem of explaining differences in survival behaviour, those approaches rely on (assumptions of) predictive features followed by risk stratification. In other words, they lack the ability to discover new information on factors related to survival. In contrast, we approach such a problem from the perspective of descriptive supervised pattern mining to discover local patterns associated with different survival behaviours. Hence, we introduce the EsmamDS algorithm: an Exceptional Model Mining framework to provide straightforward characterisations of subgroups presenting unusual survival models -- given by the Kaplan-Meier estimates. This work builds on the Esmam algorithm to address the problem of pattern redundancy and provide a more informative and diverse characterisation of survival behaviour.