Saved in:
Bibliographic Details
Main Authors: Brockschmidt, Marie, Schröder, Maresa, Feuerriegel, Stefan
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.22352
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911423506939904
author Brockschmidt, Marie
Schröder, Maresa
Feuerriegel, Stefan
author_facet Brockschmidt, Marie
Schröder, Maresa
Feuerriegel, Stefan
contents Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death. Unlike standard tabular data, survival data often come with incomplete event information due to dropout, or loss to follow-up. This poses unique challenges for synthetic data generation, where it is crucial for clinical research to faithfully reproduce both the event-time distribution and the censoring mechanism. In this paper, we propose SurvDiff an end-to-end diffusion model specifically designed for generating synthetic data in survival analysis. SurvDiff is tailored to capture the data-generating mechanism by jointly generating mixed-type covariates, event times, and right-censoring, guided by a survival-tailored loss function. The loss encodes the time-to-event structure and directly optimizes for downstream survival tasks, which ensures that SurvDiff (i) reproduces realistic event-time distributions and (ii preserves the censoring mechanism. Across multiple datasets, we show that SurvDiff consistently outperforms state-of-the-art generative baselines in both distributional fidelity and survival model evaluation metrics across multiple medical datasets. To the best of our knowledge, SurvDiff is the first end-to-end diffusion model explicitly designed for generating synthetic survival data.
format Preprint
id arxiv_https___arxiv_org_abs_2509_22352
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
Brockschmidt, Marie
Schröder, Maresa
Feuerriegel, Stefan
Machine Learning
Artificial Intelligence
Survival analysis is a cornerstone of clinical research by modeling time-to-event outcomes such as metastasis, disease relapse, or patient death. Unlike standard tabular data, survival data often come with incomplete event information due to dropout, or loss to follow-up. This poses unique challenges for synthetic data generation, where it is crucial for clinical research to faithfully reproduce both the event-time distribution and the censoring mechanism. In this paper, we propose SurvDiff an end-to-end diffusion model specifically designed for generating synthetic data in survival analysis. SurvDiff is tailored to capture the data-generating mechanism by jointly generating mixed-type covariates, event times, and right-censoring, guided by a survival-tailored loss function. The loss encodes the time-to-event structure and directly optimizes for downstream survival tasks, which ensures that SurvDiff (i) reproduces realistic event-time distributions and (ii preserves the censoring mechanism. Across multiple datasets, we show that SurvDiff consistently outperforms state-of-the-art generative baselines in both distributional fidelity and survival model evaluation metrics across multiple medical datasets. To the best of our knowledge, SurvDiff is the first end-to-end diffusion model explicitly designed for generating synthetic survival data.
title SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.22352