WRSE -- a non-parametric weighted-resolution ensemble for predicting individual survival distributions in the ICU

TL;DR

This paper introduces WRSE, a non-parametric ensemble method for dynamic survival prediction in ICU patients, offering accurate, well-calibrated survival distributions with faster training times than existing models.

Contribution

The paper presents WRSE, a novel non-parametric ensemble approach that efficiently predicts individual survival distributions in ICU settings, outperforming existing models in training speed.

Findings

Competitive accuracy with state-of-the-art models

Significantly faster training times (2-9x reduction)

Effective calibration and discrimination in survival predictions

Abstract

Dynamic assessment of mortality risk in the intensive care unit (ICU) can be used to stratify patients, inform about treatment effectiveness or serve as part of an early-warning system. Static risk scoring systems, such as APACHE or SAPS, have recently been supplemented with data-driven approaches that track the dynamic mortality risk over time. Recent works have focused on enhancing the information delivered to clinicians even further by producing full survival distributions instead of point predictions or fixed horizon risks. In this work, we propose a non-parametric ensemble model, Weighted Resolution Survival Ensemble (WRSE), tailored to estimate such dynamic individual survival distributions. Inspired by the simplicity and robustness of ensemble methods, the proposed approach combines a set of binary classifiers spaced according to a decay function reflecting the relevance of short-term mortality predictions. Models and baselines are evaluated under weighted calibration and discrimination metrics for individual survival distributions which closely reflect the utility of a model in ICU practice. We show competitive results with state-of-the-art probabilistic models, while greatly reducing training time by factors of 2-9x.