Optimal Sparse Survival Trees

TL;DR

This paper introduces a dynamic programming approach to construct provably optimal sparse survival trees, enhancing interpretability and accuracy in high-stakes health-related decision-making.

Contribution

It presents a novel dynamic programming method that guarantees optimal sparse survival tree models, overcoming limitations of heuristic algorithms.

Findings

Finds optimal sparse survival trees efficiently in seconds.

Improves interpretability of survival analysis models.

Outperforms heuristic methods in accuracy and optimality.

Abstract

Interpretability is crucial for doctors, hospitals, pharmaceutical companies and biotechnology corporations to analyze and make decisions for high stakes problems that involve human health. Tree-based methods have been widely adopted for survival analysis due to their appealing interpretablility and their ability to capture complex relationships. However, most existing methods to produce survival trees rely on heuristic (or greedy) algorithms, which risk producing sub-optimal models. We present a dynamic-programming-with-bounds approach that finds provably-optimal sparse survival tree models, frequently in only a few seconds.