TabSurv: Adapting Modern Tabular Neural Networks to Survival Analysis

TL;DR

TabSurv introduces a versatile deep learning approach for survival analysis on tabular data, leveraging modern architectures, ensemble methods, and a novel loss function to outperform classical models.

Contribution

It adapts modern tabular neural networks to survival analysis with a new histogram loss and ensemble training, demonstrating superior performance on multiple datasets.

Findings

TabSurv outperforms classical and deep learning baselines in survival prediction.

Deep ensembles with Weibull parametrization achieve the highest average C-index.

The approach is effective across diverse real-world datasets.

Abstract

Survival analysis on tabular data is a well-studied problem. However, existing deep learning methods are often highly task-specific, which can limit the transfer of new approaches from other domains and introduce constraints that may affect performance. We propose TabSurv, an approach that adapts modern tabular architectures to survival analysis using either the Weibull distribution or non-parametric survival prediction. TabSurv optimizes SurvHL, a novel histogram loss function supporting censored data. In addition to a baseline feed-forward network, we implement deep ensembles of MLPs for survival analysis within TabSurv. In contrast to prior work, the ensemble components are trained in parallel, optimizing survival distribution parameters before averaging, which promotes diversity across ensemble component predictions. We perform a comprehensive empirical evaluation of different proposed architectures on 10 diverse real-world survival datasets. Our results show that TabSurv consistently outperforms on average established classical and deep learning baselines, such as RSF, DeepSurv, DeepHit, SurvTRACE. Notably, deep ensembles with Weibull parametrization instead of non-parametric models achieve the highest average rank by C-index. Overall, our study clarifies how modern tabular neural networks can be adapted and trained to tackle survival analysis problems, offering a strong and reliable approach. The TabSurv implementation is publicly available.