Differentiable sorting for censored time-to-event data

Andre Vauvelle, Benjamin Wild, Roland Eils, Spiros Denaxas

Keywords: Survival Analysis, Censored Data, Semi-supervised Learning, Time-to-event-data, Algorithmic Supervision, Sorting, Risk Prediction, Weakly-supervised Learning, Machine Learning, Cox's Partial Likelihood, Differentiable Sorting Networks, Transitive Inductive Bias, Ranking Losses, Listwise Ranking, Healthcare Applications, Deep Learning, Neural Networks, Top-k Risk Prediction

TL;DR: Diffsurv introduces a novel extension of differentiable sorting methods to survival analysis, effectively handling censored data.

Abstract: Survival analysis is a crucial semi-supervised task in machine learning with significant real-world applications, especially in healthcare. It is known that survival analysis can be reduced to a ranking task and be learnt with ordering supervision. Differentiable sorting methods have been shown to be effective in this area but are unable to handle censored orderings. To combat this, we propose Diffsurv, which predicts matrices of \emph{possible} permutations that accommodate the label uncertainty introduced by censored samples. Our experiments reveal that Diffsurv matches or outperforms established baselines in various semi-simulated and real-world risk prediction scenarios.

Submission Number: 59