Bioequivalence (BE) studies are clinical trials essential in demonstrating therapeutic equivalence across generic and reference medicinal products. Unfortunately, the lack of large samples and broad confidence intervals (CIs) limits their effectiveness. We present a hybrid data augmentation framework in this study that merges actual clinical and synthetic pharmacokinetic (PK) data generation with Wasserstein Generative Adversarial Networks (WGANs). Three randomized, single-dose, 2 × 2 crossover BE datasets (lisinopril, amlodipine, and aceclofenac) were used to develop WGAN-based analyses to directly convert them to virtual subject data. Hybrid datasets were generated by pooling real and synthetic data in fixed proportions while keeping a constant real sample amount. The hybrid datasets were analysed with respect to baseline BE metrics, including geometric mean ratio (GMR), 90% CI, as well as within-subject variability over PK data components, including AUC, Cmax, and the recently proposed average slope (AS). Hybrid datasets achieved a significant reduction in 90% CI widths, with an average reduction of up to 6.7% across all drugs and parameters. For example, in the case of aceclofenac and Cmax, the hybrid 50–150 model reduced the width by approximately 59.8%, decreasing from 18.86% to 7.59%. These results suggest that WGAN-based hybrid datasets can improve the statistical robustness and reproducibility of BE assessments if used as supporting evidence. Whilst clinical data needs to be the foundation for regulatory decisions, hybrid data may be useful for study design minimization and design, sensitivity assessment, and uncertainty reduction particularly in areas where large-scale recruitment is not feasible or an ethically untenable condition.
- Open Access
- Article
The Use of Generative AI to Create Hybrid Populations for Bioequivalence Trials
Author Information
Received: 23 Dec 2025 | Revised: 27 Jan 2026 | Accepted: 05 Mar 2026 | Published: 27 Mar 2026
Abstract
Keywords
Wasserstein Generative Adversarial Networks | generative AI | data augmentation | hybrid datasets | bioequivalence studies
References
- 1.
Julious, S.A. Sample Sizes for Clinical Trials, 2nd ed.; Chapman and Hall/CRC: New York, NY, USA, 2023. https://doi.org/10.1201/9780429503658.
- 2.
Endrenyi, L.; Tothfalusi, L. Sample Sizes for Designing Bioequivalence Studies for Highly Variable Drugs. J. Pharm. Pharm. Sci. 2011, 15, 73–84. https://doi.org/10.18433/J3Z88F.
- 3.
Nayyar, A.; Gadhavi, L.; Zaman, N. Machine Learning in Healthcare: Review, Opportunities and Challenges. In Machine Learning and the Internet of Medical Things in Healthcare; Elsevier: Amsterdam, The Netherlands, 2021; pp. 23–45. https://doi.org/10.1016/B978-0-12-821229-5.00011-2.
- 4.
Goodfellow, I.; Pouget-Abadie, J.; Mirza, M.; et al. Generative Adversarial Networks. Commun. ACM 2020, 63, 139–144. https://doi.org/10.1145/3422622.
- 5.
Piacentino, E.; Guarner, A.; Angulo, C. Generating Synthetic ECGs Using GANs for Anonymizing Healthcare Data. Electronics 2021, 10, 389. https://doi.org/10.3390/electronics10040389.
- 6.
Kumar Swarnkar, S.; Guru, A.; Chhabra, G.S.; et al. Artificial Intelligence Revolutionizing Cancer Care: Precision Diagnosis and Patient-Centric Healthcare, 1st ed.; CRC Press: Boca Raton, FL, USA, 2024. https://doi.org/10.1201/9781003571339.
- 7.
Arjovsky, M.; Chintala, S.; Bottou, L. Wasserstein GAN. arXiv 2017, arXiv:1701.07875.
- 8.
Gulrajani, I.; Ahmed, F.; Arjovsky, M.; et al. Improved Training of Wasserstein GANs. arXiv 2017, arXiv:1704.00028.
- 9.
European Medicines Agency, Committee for Medicinal Products for Human Use (CHMP). Guideline on the Investigation of Bioequivalence. CPMP/EWP/QWP/1401/98 Rev. 1/Corr 2010. Available online: https://www.ema.europa.eu/en/documents/scientific-guideline/guideline-investigation-bioequivalence-rev1_en.pdf (accessed on 22 December 2025).
- 10.
U.S. Food and Drug Administration (FDA). Bioavailability and Bioequivalence Studies Submitted in NDAs or INDs—General Considerations. Available online: https://www.fda.gov/regulatory-information/search-fda-guidance-documents/bioavailability-and-bioequivalence-studies-submitted-ndas-or-inds-general-considerations (accessed on 22 December 2025).
- 11.
Bioequivalence for Immediate-Release Solid Oral Dosage Forms, M13A. Available online: https://database.ich.org/sites/default/files/ICH_M13A_Step4_Final_Guideline_2024_0723.pdf (accessed on 25 March 2026).
- 12.
Farhadi, A.; Taheri, A. Application of GenAI in Synthetic Data Generation in the Healthcare System. In Application of Generative AI in Healthcare Systems; Springer: Cham, Switzerland, 2025; pp. 67–89. https://doi.org/10.1007/978-3-031-82963-5_3.
- 13.
Rashidieranjbar, F; Farhadi, A.; Zamanifar, A. Revolutionizing Healthcare with Generative Artificial Intelligence Technologies. In Generative Artificial Intelligence (AI) Approaches for Industrial Applications; Springer: Cham, Switzerland, 2025; pp. 189–221. https://doi.org/10.1007/978-3-031-76710-4_10.
- 14.
Farhadi, A.; Zamanifar, A.; Faezipour, M. Application of Generative AI in Drug Discovery. In Application of Generative AI in Healthcare Systems; Springer: Cham, Switzerland, 2025; pp. 155–174. https://doi.org/10.1007/978-3-031-82963-5_6.
- 15.
Nikolopoulos, A.; Karalis, V.D. Artificial Intelligence Meets Bioequivalence: Using Generative Adversarial Networks for Smarter, Smaller Trials. Mach. Learn. Knowl. Extr. 2025, 7, 47. https://doi.org/10.3390/make7020047.
- 16.
Nikolopoulos, A.; Karalis, V.D. Implementation of a Generative AI Algorithm for Virtually Increasing the Sample Size of Clinical Studies. Appl. Sci. 2024, 14, 4570. https://doi.org/10.3390/app14114570.
- 17.
Nikolopoulos, A.; Karalis, V.D. Generative Neural Networks for Addressing the Bioequivalence of Highly Variable Drugs. Algorithms 2025, 18, 266. https://doi.org/10.3390/a18050266.
- 18.
Papadopoulos, D.; Karalis, V.D. Variational Autoencoders for Data Augmentation in Clinical Studies. Appl. Sci. 2023, 13, 8793. https://doi.org/10.3390/app13158793.
- 19.
Papadopoulos, D.; Karalis, V.D. Introducing an Artificial Neural Network for Virtually Increasing the Sample Size of Bioequivalence Studies. Appl. Sci. 2024, 14, 2970. https://doi.org/10.3390/app14072970.
- 20.
Papadopoulos, D.; Karali, G.; Karalis, V.D. Bioequivalence Studies of Highly Variable Drugs: An Old Problem Addressed by Artificial Neural Networks. Appl. Sci. 2024, 14, 5279. https://doi.org/10.3390/app14125279.
- 21.
Karalis, V.D. An In Silico Approach toward the Appropriate Absorption Rate Metric in Bioequivalence. Pharmaceuticals 2023, 16, 725. https://doi.org/10.3390/ph16050725.
- 22.
Li, T.; Liu, Y.; Liu, S.; et al. Bioequivalence Evaluation and Food Effect Assessment of Lisinopril/Amlodipine Tablets in Healthy Chinese Subjects under Fasting and Fed Conditions. BMC Pharmacol. Toxicol. 2022, 23, 45. https://doi.org/10.1186/s40360-022-00590-6.
- 23.
Bushra, R.; Shoaib, M.H.; Ali, H.; et al. Pharmacokinetics and Bioequivalence Assessment of Optimized Directly Compressible Aceclofenac (100 Mg) Tablet Formulation in Healthy Human Subjects. PLoS ONE 2020, 15, e0238951. https://doi.org/10.1371/journal.pone.0238951.
- 24.
Karalis, V.D. On the Interplay between Machine Learning, Population Pharmacokinetics, and Bioequivalence to Introduce Average Slope as a New Measure for Absorption Rate. Appl. Sci. 2023, 13, 2257. https://doi.org/10.3390/app13042257.
- 25.
Shi, Y.; Li, Q.; Zhu, X. Building Footprint Generation Using Improved Generative Adversarial Networks. IEEE Geosci. Remote Sens. Lett. 2018, 16, 603–607. https://doi.org/10.1109/LGRS.2018.2878486.
- 26.
Bhat, R.; Nanjundegowda, R. A Review on Comparative Analysis of Generative Adversarial Networks’ Architectures and Applications. J. Robot. Control 2024, 6, 53–64. https://doi.org/10.18196/jrc.v6i1.24160.
- 27.
Sengar, S.S.; Hasan, A.B.; Kumar, S.; et al. Generative Artificial Intelligence: A Systematic Review and Applications. Multimed. Tools Appl. 2024, 84, 23661–23700. https://doi.org/10.1007/s11042-024-20016-1.
- 28.
Fleming, N. Computer-Calculated Compounds: Researchers Are Developing Artificial Intelligence to Discover Drugs. Nature 2018, 557, S55–S57. https://doi.org/10.1038/d41586-018-05267-X.
- 29.
Beam, A.L.; Kohane, I.S. Big Data and Machine Learning in Health Care. JAMA 2018, 319, 1317–1318. https://doi.org/10.1001/jama.2017.18391.
- 30.
Committee for Medicinal Products for Human Use (CHMP) Committee for Medicinal Products for Veterinary Use (CVMP). Reflection Paper on the Use of Artificial Intelligence (AI) in the Medicinal Product Lifecycle. Available online: https://www.ema.europa.eu/en/documents/scientific-guideline/reflection-paper-use-artificial-intelligence-ai-medicinal-product-lifecycle_en.pdf (accessed on 25 March 2026).
- 31.
U.S. Food and Drug Administration. Using Artificial Intelligence & Machine Learning in the Development of Drug and Biological Products. Available online: https://www.federalregister.gov/documents/2023/05/11/2023-09985/using-artificial-intelligence-and-machine-learning-in-the-development-of-drug-and-biological (accessed on 25 March 2026).
- 32.
Lucic, M.; Kurach, K.; Michalski, M.; et al. Are GANs Created Equal? A Large-Scale Study. arXiv 2017, arXiv:1711.10337.
- 33.
Karras, T.; Laine, S.; Aila, T. A Style-Based Generator Architecture for Generative Adversarial Networks. arXiv 2018, arXiv:1812.04948.
- 34.
Brock, A.; Donahue, J.; Simonyan, K. Large Scale GAN Training for High Fidelity Natural Image Synthesis. arXiv 2018, arXiv:1809.11096.
- 35.
Salimans, T.; Goodfellow, I.; Zaremba, W.; et al. Improved Techniques for Training GANs. arXiv 2016, arXiv:1606.03498.
- 36.
Frid-Adar, M.; Klang, E.; Amitai, M; et al. Synthetic Data Augmentation Using GAN for Improved Liver Lesion Classification. arXiv 2018, arXiv:1801.02385.
- 37.
Baowaly, M.K.; Lin, C.-C.; Liu, C.-L.; et al. Synthesizing Electronic Health Records Using Improved Generative Adversarial Networks. J. Am. Med. Inform. Assoc. 2018, 26, 228–241. https://doi.org/10.1093/jamia/ocy142.
- 38.
Choi, E.; Biswal, S; Malin, B.; et al. Generating Multi-Label Discrete Patient Records Using Generative Adversarial Networks. arXiv 2017, arXiv:1703.06490.
- 39.
Papin, J.A.; Mac Gabhann, F.; Sauro, H.M.; et al. Improving Reproducibility in Computational Biology Research. PLoS Comput. Biol. 2020, 16, e1007881. https://doi.org/10.1371/journal.pcbi.1007881.
- 40.
Hutson, M. Artificial Intelligence Faces Reproducibility Crisis. Science 2018, 359, 725–726. https://doi.org/10.1126/science.359.6377.725.
- 41.
Mittelstadt, B. Principles Alone Cannot Guarantee Ethical AI. Nat. Mach. Intell. 2019, 1, 501–507. https://doi.org/10.1038/s42256-019-0114-4.
- 42.
Floridi, L.; Cowls, J. A Unified Framework of Five Principles for AI in Society. Harv. Data Sci. Rev. 2019, 1. https://doi.org/10.1162/99608f92.8cd550d1.
- 43.
Jobin, A.; Ienca, M.; Vayena, E. The Global Landscape of AI Ethics Guidelines. Nat. Mach. Intell. 2019, 1, 389–399. https://doi.org/10.1038/s42256-019-0088-2.
- 44.
Parasrampuria, S.; Sertkaya, A.; Lord, A.; et al. Cost of Generic Drug Development and Approval; U.S. Department of Health and Human Services, Office of the Assistant Secretary for Planning and Evaluation: Washington, DC, USA, 2021. Available online: https://aspe.hhs.gov/sites/default/files/documents/20e14b66420440b9e726c61d281cc5a5/cost-of-generic-drugs-erg.pdf (accessed on 25 March 2026).
- 45.
Jones, H.; Chen, Y.; Gibson, C.; et al. Physiologically Based Pharmacokinetic Modeling in Drug Discovery and Development: A Pharmaceutical Industry Perspective. Clin. Pharmacol. Ther. 2015, 97, 247–262. https://doi.org/10.1002/cpt.37.
- 46.
Mirza, M.; Osindero, S. Conditional Generative Adversarial Nets. arXiv 2014, arXiv:1411.1784.
- 47.
Holzinger, A.; Biemann, C.; Pattichis, C.S.; et al. What Do We Need to Build Explainable AI Systems for the Medical Domain? arXiv 2017, arXiv:1712.09923.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com