SurvDiff: A Diffusion Model for Generating Synthetic Data in Survival Analysis
On the map: Diffusion models → Medical imaging and segmentation
Abstract (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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models. Builds on 36 of its 71 references that are in the map. First posted on arXiv 26 Sep 2025.
Builds on
36 of 71 references.
References · 36
- 2020Denoising Diffusion Probabilistic Modelscited by 21,076
- 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
- 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
- 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
- 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
- 2016Deep Learning with Differential Privacycited by 2,728
- 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,719
- 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,323
- 2024Simple and Effective Masked Diffusion Language Modelscited by 848
- 2019Modeling Tabular data using Conditional GANcited by 699
24 more
- 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
- 2024Simplified and Generalized Masked Diffusion for Discrete Datacited by 626
- 2022TabDDPM: Modelling Tabular Data with Diffusion Modelscited by 377
- 2017The Effectiveness of Data Augmentation in Image Classification using Deep Learningcited by 370
- 2016DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Networkcited by 358
- 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 333
- 2016Ladder Variational Autoencoderscited by 318
- 2023Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Spacecited by 186
- 2021DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networkscited by 109
- 2023Deep Learning for Survival Analysis: A Reviewcited by 75
- 2024An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimizationcited by 73
- 2024TabDiff: a Mixed-type Diffusion Model for Tabular Data Generationcited by 63
- 2016Deep Survival Analysiscited by 61
- 2022A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Modelscited by 43
- 2025A Comprehensive Survey of Synthetic Tabular Data Generationcited by 28
- 2023SurvivalGAN: Generating Time-to-Event Data for Survival Analysiscited by 17
- 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
- 2020A General Machine Learning Framework for Survival Analysiscited by 12
- 2022DeepPAMM: Deep Piecewise Exponential Additive Mixed Models for Complex Hazard Structures in Survival Analysiscited by 12
- 2025Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Datacited by 10
- 2024Generating Survival Interpretable Trajectories and Datacited by 3
- 2025A Diffusion-Based Method for Learning the Multi-Outcome Distribution of Medical Treatmentscited by 3
- 2024Generating Accurate Synthetic Survival Data by Conditioning on Outcomescited by 2
- 2025Censor Dependent Variational Inferencecited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Synthetic Survival Data Generation for Heart Failure Prognosis Using Deep Generative Models
- 2026Counterfactual Understanding via Retrieval-aware Multimodal Modeling for Time-to-Event Survival Prediction
- 2026Causal Diffusion Models for Counterfactual Outcome Distributions in Longitudinal Data
- 2024CK4Gen: A Knowledge Distillation Framework for Generating High-Utility Synthetic Survival Datasets in Healthcare
- 2025Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints
- 2026Multimodal Survival Analysis with Locally Deployable Large Language Models
- 2026CACSurv: Concordance-Aligned Comparative Learning with Large Language Models for Cancer Survival Prediction
- 2026From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model