Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials
This study introduces artificial intelligence as a powerful tool to transform bioequivalence (BE) trials. We apply advanced generative models, specifically Wasserstein Generative Adversarial Networks (WGANs), to create virtual subjects and reduce the need for real human participants in generic drug...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-05-01
|
| Series: | Machine Learning and Knowledge Extraction |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-4990/7/2/47 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849432020703248384 |
|---|---|
| author | Anastasios Nikolopoulos Vangelis D. Karalis |
| author_facet | Anastasios Nikolopoulos Vangelis D. Karalis |
| author_sort | Anastasios Nikolopoulos |
| collection | DOAJ |
| description | This study introduces artificial intelligence as a powerful tool to transform bioequivalence (BE) trials. We apply advanced generative models, specifically Wasserstein Generative Adversarial Networks (WGANs), to create virtual subjects and reduce the need for real human participants in generic drug assessment. Although BE studies typically involve small sample sizes (usually 24 subjects), which may limit the use of AI-generated populations, our findings show that these models can successfully overcome this challenge. To show the utility of generative AI algorithms in BE testing, this study applied Monte Carlo simulations of 2 × 2 crossover BE trials, combined with WGANs. After training of the WGAN model, several scenarios were explored, including sample size, the proportion of subjects used for the synthesis of virtual subjects, and variabilities. The performance of the AI-synthesized populations was tested in two ways: (a) first, by assessing the similarity of the performance with the actual population, and (b) second, by evaluating the statistical power achieved, which aimed to be as high as that of the entire original population. The results demonstrated that WGANs could generate virtual populations with BE acceptance percentages and similarity levels that matched or exceeded those of the original population. This approach proved effective across various scenarios, enhancing BE study sample sizes, reducing costs, and accelerating trial durations. This study highlights the potential of WGANs to improve data augmentation and optimize subject recruitment in BE studies. |
| format | Article |
| id | doaj-art-e175695afddc475d81f0c1441399e353 |
| institution | Kabale University |
| issn | 2504-4990 |
| language | English |
| publishDate | 2025-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machine Learning and Knowledge Extraction |
| spelling | doaj-art-e175695afddc475d81f0c1441399e3532025-08-20T03:27:28ZengMDPI AGMachine Learning and Knowledge Extraction2504-49902025-05-01724710.3390/make7020047Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller TrialsAnastasios Nikolopoulos0Vangelis D. Karalis1Department of Pharmacy, School of Health Sciences, National and Kapodistrian University of Athens, 15784 Athens, GreeceDepartment of Pharmacy, School of Health Sciences, National and Kapodistrian University of Athens, 15784 Athens, GreeceThis study introduces artificial intelligence as a powerful tool to transform bioequivalence (BE) trials. We apply advanced generative models, specifically Wasserstein Generative Adversarial Networks (WGANs), to create virtual subjects and reduce the need for real human participants in generic drug assessment. Although BE studies typically involve small sample sizes (usually 24 subjects), which may limit the use of AI-generated populations, our findings show that these models can successfully overcome this challenge. To show the utility of generative AI algorithms in BE testing, this study applied Monte Carlo simulations of 2 × 2 crossover BE trials, combined with WGANs. After training of the WGAN model, several scenarios were explored, including sample size, the proportion of subjects used for the synthesis of virtual subjects, and variabilities. The performance of the AI-synthesized populations was tested in two ways: (a) first, by assessing the similarity of the performance with the actual population, and (b) second, by evaluating the statistical power achieved, which aimed to be as high as that of the entire original population. The results demonstrated that WGANs could generate virtual populations with BE acceptance percentages and similarity levels that matched or exceeded those of the original population. This approach proved effective across various scenarios, enhancing BE study sample sizes, reducing costs, and accelerating trial durations. This study highlights the potential of WGANs to improve data augmentation and optimize subject recruitment in BE studies.https://www.mdpi.com/2504-4990/7/2/47artificial neural networkgenerative adversarial networksgenerative AI algorithmsbioequivalencesample sizeclinical trials |
| spellingShingle | Anastasios Nikolopoulos Vangelis D. Karalis Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials Machine Learning and Knowledge Extraction artificial neural network generative adversarial networks generative AI algorithms bioequivalence sample size clinical trials |
| title | Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials |
| title_full | Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials |
| title_fullStr | Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials |
| title_full_unstemmed | Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials |
| title_short | Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials |
| title_sort | artificial intelligence meets bioequivalence using generative adversarial networks for smarter smaller trials |
| topic | artificial neural network generative adversarial networks generative AI algorithms bioequivalence sample size clinical trials |
| url | https://www.mdpi.com/2504-4990/7/2/47 |
| work_keys_str_mv | AT anastasiosnikolopoulos artificialintelligencemeetsbioequivalenceusinggenerativeadversarialnetworksforsmartersmallertrials AT vangelisdkaralis artificialintelligencemeetsbioequivalenceusinggenerativeadversarialnetworksforsmartersmallertrials |