SurvFM enables tabular foundation models for right-censored survival prediction
Abstract
General-purpose tabular foundation models can be adapted across prediction tasks, but right censoring leaves many event times unknown and prevents their direct use as regression labels. SurvFM converts censored follow-up into observation-level targets for restricted mean survival time (RMST), the expected event-free time accumulated up to a chosen horizon. These targets allow multiple tabular foundation models to predict RMST without architectural modification. In simulations with known RMST, SurvFM achieved leading RMST accuracy and competitive discrimination across heterogeneous settings. Its targets were more accurate than simpler outcome constructions, with larger gains as censoring increased. Across 55 public datasets, SurvFM models remained in the leading performance band under full and restricted training. Models fitted in either of two public myelodysplastic syndrome cohorts retained competitive performance in the other without refitting. SurvFM separates censoring handling from prediction architecture, allowing advances in general-purpose tabular prediction to enter survival analysis without model-specific redesign.
Related
- Conformal Prediction and Conditional Coverage for Tabular Foundation Models
- Tabular foundation models are not a shortcut to calibrated clinical risk prediction: a pre-registered simulation against the true risk
- Locally Estimated Scatterplot Smoothing for Censored Survival Data
- SMOOTH DIVERGENCES ESTIMATION FOR CENSORED SURVIVAL DATA
- Can Tabular Foundation Models Amortize Statistical Inference?
BibTeX
@misc{lyu2026survfm,
title = {{SurvFM enables tabular foundation models for right-censored survival prediction}},
author = {Yue Lyu and Steven H. Lin and Xuelin Huang and Ziyi Li},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2607.09577},
eprint = {2607.09577},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.09577},
}
RIS
TY - UNPB
TI - SurvFM enables tabular foundation models for right-censored survival prediction
AU - Yue Lyu
AU - Steven H. Lin
AU - Xuelin Huang
AU - Ziyi Li
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2607.09577
UR - https://arxiv.org/abs/2607.09577
AB - General-purpose tabular foundation models can be adapted across prediction tasks, but right censoring leaves many event times unknown and prevents their direct use as regression labels. SurvFM converts censored follow-up into observation-level targets for restricted mean survival time (RMST), the expected event-free time accumulated up to a chosen horizon. These targets allow multiple tabular foundation models to predict RMST without architectural modification. In simulations with known RMST, SurvFM achieved leading RMST accuracy and competitive discrimination across heterogeneous settings. Its targets were more accurate than simpler outcome constructions, with larger gains as censoring increased. Across 55 public datasets, SurvFM models remained in the leading performance band under full and restricted training. Models fitted in either of two public myelodysplastic syndrome cohorts retained competitive performance in the other without refitting. SurvFM separates censoring handling from prediction architecture, allowing advances in general-purpose tabular prediction to enter survival analysis without model-specific redesign.
ER -