Conformalized Survival Distributions: A Generic Post-Process to Increase Calibration

TL;DR

This paper proposes a conformal regression method to enhance calibration in survival analysis models without sacrificing discrimination, backed by theoretical guarantees and validated on multiple real-world datasets.

Contribution

It introduces a novel conformal post-processing technique that improves calibration in survival models while maintaining discrimination, supported by theoretical and empirical validation.

Findings

Improves calibration without reducing discrimination performance.

Provides theoretical guarantees for calibration enhancement.

Validated across 11 real-world datasets, demonstrating robustness.

Abstract

Discrimination and calibration represent two important properties of survival analysis, with the former assessing the model's ability to accurately rank subjects and the latter evaluating the alignment of predicted outcomes with actual events. With their distinct nature, it is hard for survival models to simultaneously optimize both of them especially as many previous results found improving calibration tends to diminish discrimination performance. This paper introduces a novel approach utilizing conformal regression that can improve a model's calibration without degrading discrimination. We provide theoretical guarantees for the above claim, and rigorously validate the efficiency of our approach across 11 real-world datasets, showcasing its practical applicability and robustness in diverse scenarios.