A framework for leveraging machine learning tools to estimate personalized survival curves

TL;DR

This paper introduces a flexible framework leveraging machine learning tools to estimate personalized survival curves by decomposing the survival function into observable regression models, enabling broader application beyond traditional methods.

Contribution

It proposes a novel decomposition approach that simplifies survival function estimation, allowing the use of diverse machine learning methods without complex handling of censoring or truncation.

Findings

Effective estimation of survival curves demonstrated on HIV trial data

Flexible regression methods outperform traditional models in accuracy

Framework applicable to various survival analysis contexts

Abstract

The conditional survival function of a time-to-event outcome subject to censoring and truncation is a common target of estimation in survival analysis. This parameter may be of scientific interest and also often appears as a nuisance in nonparametric and semiparametric problems. In addition to classical parametric and semiparametric methods (e.g., based on the Cox proportional hazards model), flexible machine learning approaches have been developed to estimate the conditional survival function. However, many of these methods are either implicitly or explicitly targeted toward risk stratification rather than overall survival function estimation. Others apply only to discrete-time settings or require inverse probability of censoring weights, which can be as difficult to estimate as the outcome survival function itself. Here, we employ a decomposition of the conditional survival function in terms of observable regression models in which censoring and truncation play no role. This allows application of an array of flexible regression and classification methods rather than only approaches that explicitly handle the complexities inherent to survival data. We outline estimation procedures based on this decomposition, empirically assess their performance, and demonstrate their use on data from an HIV vaccine trial.