A novel digital twin strategy to examine the implications of randomized clinical trials for real-world populations - PubMed
4 days ago
- #randomized clinical trials
- #digital twin
- #real-world data
- A novel digital twin strategy, RCT-Twin-GAN, was developed to examine the implications of randomized clinical trials (RCTs) for real-world populations.
- The model leverages relationships between covariates and outcomes to generate a digital twin of an RCT conditioned on covariate distributions from a second patient population.
- The strategy was tested by reproducing the treatment effects of the SPRINT and ACCORD Blood Pressure Trials, demonstrating balanced treatment arms and similar outcomes.
- The digital twins showed that SPRINT-conditioned ACCORD-Twins reproduced the non-significant outcome seen in ACCORD, while ACCORD-conditioned SPRINT-Twins reproduced the significant outcome seen in SPRINT.
- The approach was also applied to a real-world population in electronic health records, simulating the translation of RCT-derived treatment effects across different patient populations.
- The authors declare no competing financial or non-financial interests, though several have patents, advisory roles, or funding from various organizations.