Counterfactual explanation of machine learning survival models
This addresses the interpretability challenge for survival models in fields like healthcare, though it is incremental as it adapts existing explanation techniques to a specific model type.
The authors tackled the problem of explaining machine learning survival models by proposing a method for generating counterfactual explanations, showing that it reduces to a convex optimization problem for Cox models and using Particle Swarm Optimization for other models, with validation through numerical experiments on real and synthetic data.
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.