Generative Neural Networks for Addressing the Bioequivalence of Highly Variable Drugs

Abstract

Bioequivalence assessment of highly variable drugs (HVDs) remains a significant challenge, as the application of scaled approaches requires replicate designs, complex statistical analyses, and varies between regulatory authorities (e.g., FDA and EMA). This study introduces the use of artificial intelligence, specifically Wasserstein Generative Adversarial Networks (WGANs), as a novel approach for bioequivalence studies of HVDs. Monte Carlo simulations were conducted to evaluate the performance of WGANs across various variability levels, population sizes, and data augmentation scales (2× and 3×). The generated data were tested for bioequivalence acceptance using both EMA and FDA scaled approaches. The WGAN approach, even applied without scaling, consistently outperformed the scaled EMA/FDA methods by effectively reducing the required sample size. Furthermore, the WGAN approach not only minimizes the sample size needed for bioequivalence studies of HVDs, but also eliminates the need for complex, costly, and time-consuming replicate designs that are prone to high dropout rates. This study demonstrates that using WGANs with 3× data augmentation can achieve bioequivalence acceptance rates exceeding 89% across all FDA and EMA criteria, with 10 out of 18 scenarios reaching 100%, highlighting the WGAN method potential to transform the design and efficiency of bioequivalence studies. This is a foundational step in utilizing WGANs for the bioequivalence assessment of HVDs, highlighting that with clear regulatory criteria, a new era for bioequivalence evaluation can begin.