SurvCORN: Survival Analysis with Conditional Ordinal Ranking Neural Network
This addresses survival prediction challenges with censored data in healthcare, offering incremental improvements to prognosis accuracy.
The paper tackles survival analysis in healthcare by proposing SurvCORN, a method using conditional ordinal ranking networks to predict survival curves, and introduces SurvMAE as an evaluation metric. It demonstrates on two cancer datasets that SurvCORN improves time-to-event predictions while maintaining accurate patient outcome ordering.
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.