SurvCORN: Survival Analysis with Conditional Ordinal Ranking Neural Network

TL;DR

SurvCORN introduces a neural network-based method for survival analysis that effectively handles censored data and predicts individual survival curves, improving accuracy in healthcare prognosis.

Contribution

This paper extends ordinal regression techniques to survival analysis with censored data, proposing SurvCORN and a new evaluation metric SurvMAE for better prognosis predictions.

Findings

SurvCORN accurately ranks patient outcomes in real-world datasets.

The method improves individual time-to-event prediction accuracy.

SurvCORN outperforms existing survival analysis models.

Abstract

Survival analysis plays a crucial role in estimating the likelihood of future events for patients by modeling time-to-event data, particularly in healthcare settings where predictions about outcomes such as death and disease recurrence are essential. However, this analysis poses challenges due to the presence of censored data, where time-to-event information is missing for certain data points. Yet, censored data can offer valuable insights, provided we appropriately incorporate the censoring time during modeling. In this paper, we propose SurvCORN, a novel method utilizing conditional ordinal ranking networks to predict survival curves directly. Additionally, we introduce SurvMAE, a metric designed to evaluate the accuracy of model predictions in estimating time-to-event outcomes. Through empirical evaluation on two real-world cancer datasets, we demonstrate SurvCORN's ability to maintain accurate ordering between patient outcomes while improving individual time-to-event predictions. Our contributions extend recent advancements in ordinal regression to survival analysis, offering valuable insights into accurate prognosis in healthcare settings.