Toward Valid Generative Clinical Trial Data with Survival Endpoints

Perrine Chassat, Van Tuan NGUYEN, Lucas Ducrot, Emilie Lanoy, Agathe Guilloux

Keywords: Generative models, Clinical trial simulation, Survival endpoints, Variational autoencoder (VAE), Type I error and power, Control arm augmentation, Privacy-preserving data sharing

TL;DR: We introduce a VAE model for generating synthetic survival data in clinical trials, improving fidelity, utility, and privacy over existing methods while enabling valid external controls and trial simulations.

Track: Proceedings

Abstract:

Clinical trials face mounting challenges: fragmented patient populations, slow enrollment, and unsustainable costs, particularly for late phase trials in oncology and rare diseases. While external control arms built from real-world data have been explored, a promising alternative is the generation of synthetic control arms using generative AI. A central challenge is the generation of time-to-event outcomes, which constitute primary endpoints in oncology and rare disease trials, but are difficult to model under censoring and small sample sizes. Existing generative approaches, largely GAN-based, are data-hungry, unstable, and rely on strong assumptions such as independent censoring.
We introduce a variational autoencoder (VAE) that jointly generates mixed-type covariates and survival outcomes within a unified latent variable framework, without assuming independent censoring. Across synthetic and real trial datasets, we evaluate our model in two realistic scenarios: (i) data sharing under privacy constraints, where synthetic controls substitute for original data, and (ii) control-arm augmentation, where synthetic patients mitigate imbalances between treated and control groups. Our method outperforms GAN baselines on fidelity, utility, and privacy metrics, while revealing systematic miscalibration of type I error and power. We propose a post-generation selection procedure that improves calibration, highlighting both progress and open challenges for generative survival modeling.

General Area: Models and Methods

Specific Subject Areas: Survival Analysis, Bayesian & Probabilistic Methods, Public & Social Health, Evaluation Methods & Validity, Privacy & Security

Data And Code Availability: Yes

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Code URL: https://github.com/aguilloux/survgen-clinical-trials

Submission Number: 109