Evaluating virtual-control-augmented trials for reproducing treatment effect from original RCTs
Abstract
This study investigates the use of virtual patient data to augment control arms in randomised controlled trials (RCTs). Using data from the IST and IST3 trials, we simulated RCTs in which the recruitment in the control arms would stop after a fraction of the initially planned sample size, and would be completed by virtual patients generated by CTGAN and TVAE, two AI algorithms trained on the recruited control patients. In IST, the absolute risk difference(ARD) on death or dependency at 14 days was -0.012 (SE 0.014). Completing the control arm by CTGAN-generated virtual patients after the recruitment of 10% and 50% of participants, yielded an ARD of 0.004 (SE 0.014) (relative difference 133%) and -0.021 (SE 0.014) (relative difference 76%), respectively. Results were comparable with IST3 or TVAE. This is the first empirical demonstration of the risk of errors and misleading conclusions associated with generating virtual controls solely from trial data.
Keywords
Cite
@article{arxiv.2507.16048,
title = {Evaluating virtual-control-augmented trials for reproducing treatment effect from original RCTs},
author = {Alex Fernandes and Raphaël Porcher and Viet-Thi Tran and François Petit},
journal= {arXiv preprint arXiv:2507.16048},
year = {2025}
}