Generating Accurate Synthetic Survival Data by Conditioning on Outcomes

Mohd Ashhad, Ricardo Henao
Proceedings of the 10th Machine Learning for Healthcare Conference, PMLR 298, 2025.

Abstract

Synthetically generated data can improve privacy, fairness, and data accessibility; however, it can be challenging in specialized scenarios such as survival analysis. One key challenge in this setting is censoring, i.e., the timing of an event is unknown in some cases. Existing methods struggle to accurately reproduce the distributions of both observed and censored event times when generating synthetic data. We propose a conceptually simple approach that generates covariates conditioned on event times and censoring indicators by leveraging existing tabular data generation models without making assumptions about the mechanism underlying censoring. Experiments on real-world datasets demonstrate that our method consistently outperforms baselines and improves downstream survival model performance.

Cite this Paper

BibTeX
@InProceedings{pmlr-v298-ashhad25a, title = {Generating Accurate Synthetic Survival Data by Conditioning on Outcomes}, author = {Ashhad, Mohd and Henao, Ricardo}, booktitle = {Proceedings of the 10th Machine Learning for Healthcare Conference}, year = {2025}, editor = {Agrawal, Monica and Deshpande, Kaivalya and Engelhard, Matthew and Joshi, Shalmali and Tang, Shengpu and Urteaga, Iñigo}, volume = {298}, series = {Proceedings of Machine Learning Research}, month = {15--16 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v298/main/assets/ashhad25a/ashhad25a.pdf}, url = {https://proceedings.mlr.press/v298/ashhad25a.html}, abstract = {Synthetically generated data can improve privacy, fairness, and data accessibility; however, it can be challenging in specialized scenarios such as survival analysis. One key challenge in this setting is censoring, i.e., the timing of an event is unknown in some cases. Existing methods struggle to accurately reproduce the distributions of both observed and censored event times when generating synthetic data. We propose a conceptually simple approach that generates covariates conditioned on event times and censoring indicators by leveraging existing tabular data generation models without making assumptions about the mechanism underlying censoring. Experiments on real-world datasets demonstrate that our method consistently outperforms baselines and improves downstream survival model performance.} }
Endnote
%0 Conference Paper %T Generating Accurate Synthetic Survival Data by Conditioning on Outcomes %A Mohd Ashhad %A Ricardo Henao %B Proceedings of the 10th Machine Learning for Healthcare Conference %C Proceedings of Machine Learning Research %D 2025 %E Monica Agrawal %E Kaivalya Deshpande %E Matthew Engelhard %E Shalmali Joshi %E Shengpu Tang %E Iñigo Urteaga %F pmlr-v298-ashhad25a %I PMLR %U https://proceedings.mlr.press/v298/ashhad25a.html %V 298 %X Synthetically generated data can improve privacy, fairness, and data accessibility; however, it can be challenging in specialized scenarios such as survival analysis. One key challenge in this setting is censoring, i.e., the timing of an event is unknown in some cases. Existing methods struggle to accurately reproduce the distributions of both observed and censored event times when generating synthetic data. We propose a conceptually simple approach that generates covariates conditioned on event times and censoring indicators by leveraging existing tabular data generation models without making assumptions about the mechanism underlying censoring. Experiments on real-world datasets demonstrate that our method consistently outperforms baselines and improves downstream survival model performance.
APA
Ashhad, M. & Henao, R.. (2025). Generating Accurate Synthetic Survival Data by Conditioning on Outcomes. Proceedings of the 10th Machine Learning for Healthcare Conference, in Proceedings of Machine Learning Research 298 Available from https://proceedings.mlr.press/v298/ashhad25a.html.

Related Material