DOI: https://doi.org/10.63345/ijrmp.v11.i10.2
Roshni Sinha
Independent Researcher
Delhi, India
Abstract
Drug–drug interactions (DDIs) continue to pose significant challenges in clinical practice and pharmacotherapy management. The emerging field of artificial intelligence (AI) offers promising tools to predict and mitigate potential adverse interactions between drugs. This study investigates the potential of AI-driven DDI prediction systems by reviewing the literature up to 2021, outlining methodologies used in recent research, and analyzing statistical data from a survey of healthcare professionals. Our findings indicate that AI models, particularly those using machine learning and deep neural networks, are achieving notable accuracy improvements in predicting clinically significant DDIs. We discuss the strengths, limitations, and future prospects of these systems, highlighting the need for interdisciplinary collaboration and continuous data refinement to enhance prediction reliability and patient safety.
Keywords
AI, drug–drug interaction, machine learning, deep neural networks, clinical pharmacology, prediction systems
References
- https://www.google.com/url?sa=i&url=https%3A%2F%2Fwww.cell.com%2Fiscience%2Ffulltext%2FS2589-0042%252824%252900369-9&psig=AOvVaw1pUX45wwYBmhB1tR_ioivS&ust=1741952308731000&source=images&cd=vfe&opi=89978449&ved=0CBQQjRxqFwoTCJDCnqj8howDFQAAAAAdAAAAABAJ
- https://www.google.com/url?sa=i&url=https%3A%2F%2Fbmcbioinformatics.biomedcentral.com%2Farticles%2F10.1186%2Fs12859-020-03724-x&psig=AOvVaw1pUX45wwYBmhB1tR_ioivS&ust=1741952308731000&source=images&cd=vfe&opi=89978449&ved=0CBQQjRxqFwoTCJDCnqj8howDFQAAAAAdAAAAABAh
- Ahmed, F., Chen, Y., & Li, M. (2020). Predicting drug–drug interactions using graph convolutional networks. Bioinformatics, 36(4), 1123–1130.
- Chen, X., Wang, H., & Zhao, Y. (2017). Recent advances in computational prediction of drug–drug interactions. Current Opinion in Pharmacology, 37, 1–7.
- Garcia, R., Hernandez, L., & Patel, S. (2017). Computational models in predicting drug–drug interactions: A survey. IEEE Access, 5, 23691–23703.
- Gonzalez, M., Kim, S., & Lee, J. (2019). The role of AI in improving patient safety: A review of drug interactions. Journal of Biomedical Informatics, 97, 103–112.
- Huang, L., Chen, Q., & Zhao, X. (2019). Artificial intelligence in pharmacovigilance: A systematic review. Drug Safety, 42(2), 153–165.
- Jones, P., Smith, A., & Johnson, R. (2019). Novel algorithms in the prediction of adverse drug interactions. Bioinformatics, 35(18), 3503–3510.
- Kim, S., Park, J., & Choi, Y. (2018). Drug–drug interaction prediction based on network analysis. PLOS ONE, 13(11), e0207484.
- Kumar, R., Gupta, N., & Singh, P. (2018). Applications of neural networks in predicting drug interactions. Journal of Clinical Pharmacology, 58(3), 312–321.
- Li, Q., Zhao, D., & Xu, Z. (2018). A deep learning framework for drug–drug interaction prediction. Journal of Chemical Information and Modeling, 58(10), 2105–2112.
- Liu, H., Zhang, T., & Chen, X. (2019). Integrating multi-modal data for DDI prediction using deep neural networks. IEEE Transactions on Biomedical Engineering, 66(7), 1854–1863.
- Martin, A., Lewis, D., & Roberts, T. (2016). Machine learning approaches in drug discovery. Expert Opinion on Drug Discovery, 11(10), 1191–1200.
- Novak, P., Turner, D., & Kim, Y. (2021). Advances in DDI prediction: A review of recent methods. Briefings in Bioinformatics, 22(3), bbab123.
- O’Neil, J., Ramirez, F., & Stewart, B. (2021). Enhancing clinical decision support systems with AI: DDI prediction and beyond. Journal of Medical Systems, 45(2), 19.
- Patel, D., Singh, R., & Kumar, V. (2020). Explainable AI in drug discovery: Challenges and opportunities. Nature Reviews Drug Discovery, 19(7), 449–465.
- Roberts, T., Anderson, E., & McCarthy, G. (2018). AI in healthcare: Drug–drug interaction prediction. Future Medicine, 13(4), 359–367.
- Singh, R., Kaur, P., & Gupta, S. (2021). Emerging trends in AI for drug discovery and development. Journal of Pharmaceutical Sciences, 110(4), 1445–1455.
- Smith, J., Patel, K., & Johnson, L. (2016). Predicting adverse drug reactions using machine learning techniques. BMC Medical Informatics and Decision Making, 16(1), 82.
- Wang, L., Yang, H., & Zhou, Y. (2018). Machine learning methods for predicting drug–drug interactions. Journal of Pharmacology & Therapeutics, 8(2), 99–108.
- Wei, S., & Li, F. (2019). Deep learning for drug–drug interaction prediction. Journal of Cheminformatics, 11(1), 44.
- Zhou, Y., Li, X., & Liu, S. (2020). An overview of AI techniques for pharmacovigilance. Briefings in Bioinformatics, 21(5), 1504–1516.