Counterfactual explanation of machine learning survival models

TL;DR

This paper introduces a method for generating counterfactual explanations for machine learning survival models, utilizing convex optimization for Cox models and Particle Swarm Optimization for others, validated through experiments.

Contribution

It presents a novel approach to explain survival models by defining a new condition based on mean event times and applying appropriate optimization techniques.

Findings

Effective counterfactual explanations generated for survival models.

Method works with Cox models and other black-box models.

Numerical experiments demonstrate the approach's validity.

Abstract

A method for counterfactual explanation of machine learning survival models is proposed. One of the difficulties of solving the counterfactual explanation problem is that the classes of examples are implicitly defined through outcomes of a machine learning survival model in the form of survival functions. A condition that establishes the difference between survival functions of the original example and the counterfactual is introduced. This condition is based on using a distance between mean times to event. It is shown that the counterfactual explanation problem can be reduced to a standard convex optimization problem with linear constraints when the explained black-box model is the Cox model. For other black-box models, it is proposed to apply the well-known Particle Swarm Optimization algorithm. A lot of numerical experiments with real and synthetic data demonstrate the proposed method.