Toward Valid Generative Clinical Trial Data with Survival Endpoints

TL;DR

This paper presents a novel variational autoencoder approach for generating synthetic clinical trial data with survival endpoints, addressing challenges of censoring and small sample sizes, and improving data utility and privacy.

Contribution

A new VAE-based model for joint generation of covariates and survival outcomes without assuming independent censoring, outperforming GANs in fidelity and privacy.

Findings

VAE model outperforms GAN baselines in data fidelity and privacy.

Synthetic data improves control-arm augmentation and privacy preservation.

Calibration issues remain, but post-generation procedures help mitigate them.

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.