Saved in:
Bibliographic Details
Main Authors: Ries, Maxmillan, Seth, Sohan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.18129
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912790724214784
author Ries, Maxmillan
Seth, Sohan
author_facet Ries, Maxmillan
Seth, Sohan
contents Survival analysis is a critical tool for modeling time-to-event data. Recent deep learning-based models have reduced various modeling assumptions including proportional hazard and linearity. However, a persistent challenge remains in incorporating longitudinal covariates, with prior work largely focusing on cross-sectional features, and in assessing calibration of these models, with research primarily focusing on discrimination during evaluation. We introduce TraCeR, a transformer-based survival analysis framework for incorporating longitudinal covariates. Based on a factorized self-attention architecture, TraCeR estimates the hazard function from a sequence of measurements, naturally capturing temporal covariate interactions without assumptions about the underlying data-generating process. The framework is inherently designed to handle censored data and competing events. Experiments on multiple real-world datasets demonstrate that TraCeR achieves substantial and statistically significant performance improvements over state-of-the-art methods. Furthermore, our evaluation extends beyond discrimination metrics and assesses model calibration, addressing a key oversight in literature.
format Preprint
id arxiv_https___arxiv_org_abs_2512_18129
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TraCeR: Transformer-Based Competing Risk Analysis with Longitudinal Covariates
Ries, Maxmillan
Seth, Sohan
Machine Learning
Survival analysis is a critical tool for modeling time-to-event data. Recent deep learning-based models have reduced various modeling assumptions including proportional hazard and linearity. However, a persistent challenge remains in incorporating longitudinal covariates, with prior work largely focusing on cross-sectional features, and in assessing calibration of these models, with research primarily focusing on discrimination during evaluation. We introduce TraCeR, a transformer-based survival analysis framework for incorporating longitudinal covariates. Based on a factorized self-attention architecture, TraCeR estimates the hazard function from a sequence of measurements, naturally capturing temporal covariate interactions without assumptions about the underlying data-generating process. The framework is inherently designed to handle censored data and competing events. Experiments on multiple real-world datasets demonstrate that TraCeR achieves substantial and statistically significant performance improvements over state-of-the-art methods. Furthermore, our evaluation extends beyond discrimination metrics and assesses model calibration, addressing a key oversight in literature.
title TraCeR: Transformer-Based Competing Risk Analysis with Longitudinal Covariates
topic Machine Learning
url https://arxiv.org/abs/2512.18129