Adverse Drug Reaction Prediction using Generative Adversarial Network
DOI:
https://doi.org/10.47957/ijpda.v14i2.748Keywords:
Adverse Drug Reactions (ADRs), Drug Safety, Deep Learning Regression, Data Predictive Modeling, Generative Adversarial Networks (GANs), Machine LearningAbstract
Adverse Drug Reactions (ADRs) pose significant challenges to patient safety and the effectiveness of drug therapies. This study focuses on improving drug safety by anticipating and reducing ADRs through advanced predictive modelling. By leveraging a hybrid approach that combines machine learning and deep learning techniques, along with the generation of synthetic data using Generative Adversarial Networks (GANs), the study enhances the accuracy of ADR prediction. Among the evaluated models, Deep Learning Regression demonstrated superior performance with the highest R² score (0.8222) and lowest RMSE (0.05411), indicating robust predictive capabilities. Polynomial Regression also showed promising results with the lowest MSE (0.0021). In contrast, Lasso and ElasticNet Regression models exhibited poor performance due to overfitting and negative R² values. While the results validate the efficacy of AI-based models in surpassing the limitations of traditional clinical trials and pharmacovigilance systems, further improvements in algorithm optimization and model interpretability are necessary. These advancements are essential to support the widespread adoption of AI tools in healthcare and to ensure a safer drug development lifecycle.
Downloads
References
Patrick DL, Burke LB, Powers JH, Scott JA, Rock EP, Dawisha S, et al. Title of article. Value Health. 2007;10(Suppl 2):S125-S137. doi:10.1111/j.1524-4733.2007.00275.x.
Pushparajah DS, Geissler J, Westergaard N. EUPATI: Collaboration between patients, academia, and industry to champion the informed patient in the research and development of medicines. J Med Dev Sci. 2016;1(1):74-80. doi:10.18063/jmds.v1i1.122.
Hazell L, Shakir SA. Under-reporting of adverse drug reactions. Drug Saf. 2006;29(5):385-396. doi:10.2165/00002018-200629050-00003.
ICH Expert Working Group. Post-approval safety data management: Definitions and standards for expedited reporting. ICH Harmonised Tripartite Guideline. 2003. Available from: http://www.fda.gov/cber/gdlns/ichexrep.htm
Lazarou J, Pomeranz BH, Corey PN. Incidence of adverse drug reactions in hospitalized patients: A meta-analysis of prospective studies. JAMA. 1998;279(15):1200-1205. doi:10.1001/jama.279.15.1200.
Fung M, Thornton A, Mybeck K, Wu JHH, Hornbuckle K, Muniz E. Evaluation of the characteristics of safety withdrawal of prescription drugs from worldwide pharmaceutical markets: 1960 to 1999. Ther Innov Regul Sci. 2001;35(1):293-317. doi:10.1177/009286150103500115.
Wysowski DK, Swartz L. Adverse drug event surveillance and drug withdrawals in the United States, 1969-2002: The importance of reporting suspected reactions. Arch Intern Med. 2005;165(12):1363-1369. doi:10.1001/archinte.165.12.1363.
Mulchandani R, Kakkar AK. Reporting of adverse drug reactions in India: A review of the current scenario, obstacles, and possible solutions. Int J Risk Saf Med. 2019;30(1):33-44. doi:10.3233/JRS-180228.
Alomar M. Factors affecting the development of adverse drug reactions. Saudi Pharm J. 2014;22(2):83-94. doi:10.1016/j.jsps.2013.02.003.
Biswas P. Pharmacovigilance in Asia. J Pharmacol Pharmacother. 2013;4(Suppl 1):S7-S19. doi:10.4103/0976-500X.120957.
Dal Pan GJ, Arlett PR. The US Food and Drug Administration-European Medicines Agency collaboration in pharmacovigilance: Common objectives and common challenges. Drug Saf. 2015;38:13-15. doi:10.1007/s40264-014-0259-4.
Kuhn M, Letunic I, Jensen LJ, Bork P. The SIDER database of drugs and side effects. Nucleic Acids Res. 2016;44(D1):D1075-D1079. doi:10.1093/nar/gkv1075.
Wishart DS, Knox C, Guo AC, Cheng D, Shrivastava S, Tzur D, et al. DrugBank: A knowledgebase for drugs, drug actions, and drug targets. Nucleic Acids Res. 2008;36(Database issue):D901-D906. doi:10.1093/nar/gkm958.
Wang Y, Xiao J, Suzek TO, Zhang J, Wang J, Bryant SH. PubChem: A public information system for analyzing bioactivities of small molecules. Nucleic Acids Res. 2009;37(Suppl 2):W623-W633. doi:10.1093/nar/gkp456.
Van De Waterbeemd H, Smith DA, Beaumont K, Walker DK. Property-based design: Optimization of drug absorption and pharmacokinetics. J Med Chem. 2001;44(9):1313-1333. doi:10.1021/jm0100883.
Yu J, Li N, Lin P, Li Y, Mao X, Bao G, et al. Intestinal transportations of main chemical compositions of Polygoni multiflori radix in the Caco-2 cell model. Evid Based Complement Alternat Med. 2014;2014:483641. doi:10.1155/2014/483641.
Park N, Mohammadi M, Gorde K, Jajodia S, Park H, Kim Y. Data synthesis based on generative adversarial networks. arXiv [Preprint]. 2018. doi:10.48550/arXiv.1806.03384.
Alin A. Multicollinearity. Wiley Interdiscip Rev Comput Stat. 2010;2(3):370-374. doi:10.1002/wics.84.
•Singh D, Singh B. Feature-wise normalization: An effective way of normalizing data. Pattern Recognit. 2022;122:108307. doi:10.1016/j.patcog.2021.108307.
Saeed VA, Ahmed NS, Sadiq BH. Comparative analysis of preprocessing techniques for KNN classification on the diabetes dataset. In: Proceedings of the International Conference on Innovations in Computing Research. Cham: Springer; 2024. p. 213-221.
Sta?czyk U. Feature evaluation by filter, wrapper, and embedded approaches. In: Feature Selection for Data and Pattern Recognition. Cham: Springer; 2015. p. 29-44. doi:10.1007/978-3-319-10221-8_3.
Published
How to Cite
Issue
Section
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © Author(s) retain the copyright of this article.
