paper-with-me

홈 › Papers

SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis

2025-09-26 · Marie Brockschmidt, Maresa Schröder, Stefan Feuerriegel arxiv

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.

📄 PDF Abstract BibTeX arXiv:2509.22352

Code (0)

등록된 구현이 없습니다.

Tasks

Synthetic Data Generation

Similar Papers 제목 키워드 기반

SurvivalGAN: Generating Time-to-Event Data for Survival Analysis

2023-02-24 · Alexander Norcliffe, Bogdan Cebere, Fergus Imrie, Pietro Lio 외

Synthetic data is becoming an increasingly promising technology, and successful applications can improve privacy, fairness, and data democratization. While there are many methods for generating synthetic tabular data, th…

FairnessSurvival Analysis

Conditioning on Time is All You Need for Synthetic Survival Data Generation

2024-05-27 · Mohd Ashhad, Ricardo Henao

Synthetic data generation holds considerable promise, offering avenues to enhance privacy, fairness, and data accessibility. Despite the availability of various methods for generating synthetic tabular data, challenges p…

AllFairnessSurvival AnalysisSynthetic Data Generation

Synthetic Survival Data Generation for Heart Failure Prognosis Using Deep Generative Models

2025-09-04 · Chanon Puttanawarut, Natcha Fongsrisin, Porntep Amornritvanich, Panu Looareesuwan 외 arxiv

Background: Heart failure (HF) research is constrained by limited access to large, shareable datasets due to privacy regulations and institutional barriers. Synthetic data generation offers a promising solution to overco…

Synthetic Data Generation

Neural Diffusion Processes for Physically Interpretable Survival Prediction

2025-10-01 · Alessio Cristofoletto, Cesare Rollo, Giovanni Birolo, Piero Fariselli arxiv

We introduce DeepFHT, a survival-analysis framework that couples deep neural networks with first hitting time (FHT) distributions from stochastic process theory. Time to event is represented as the first passage of a lat…

Dynamic Survival Transformers for Causal Inference with Electronic Health Records

2022-10-25 · Prayag Chatha, Yixin Wang, Zhenke Wu, Jeffrey Regier

In medicine, researchers often seek to infer the effects of a given treatment on patients' outcomes. However, the standard methods for causal survival analysis make simplistic assumptions about the data-generating proces…

Causal InferenceSurvival Analysis