Deep Reinforcement Learning-Driven Efficacy-Toxicity Balance Optimization Strategy for Personalized Drug Combination in Cancer Patients

Main Article Content

Haofeng Ye

Abstract

Precision medicine demands the careful optimization of dose regimens in cancer therapy, particularly when adjusting doses to balance therapeutic effectiveness against adverse toxicities. In this study, we introduce a deep reinforcement learning (DRL) framework that leverages multimodal patient data to optimize personalized drug combination strategies, aiming to maximize efficacy while minimizing toxicity. The DRL agent employs multi-objective reward functions to identify optimal treatment strategies by integrating genomic, clinical, and pharmacokinetic data through an advanced feature engineering pipeline. This approach was evaluated in a cohort of 2,847 cancer patients encompassing a diverse range of tumor types. Experimental results demonstrate that the algorithm improved predicted treatment response by 23.4% compared to conventional methods, while reducing serious adverse events by 18.7%. These findings highlight a significant advancement in computational approaches for personalized therapy optimization, providing clinically interpretable outputs to guide patient-specific treatment decisions.

Article Details

Section

Articles

How to Cite

Deep Reinforcement Learning-Driven Efficacy-Toxicity Balance Optimization Strategy for Personalized Drug Combination in Cancer Patients. (2025). Journal of Science, Innovation & Social Impact, 1(1), 307-317. https://sagespress.com/index.php/JSISI/article/view/35

References

1. B. Bhinder, C. Gilvary, N. S. Madhukar, and O. Elemento, "Artificial intelligence in cancer research and precision medicine," Cancer Discovery, vol. 11, no. 4, pp. 900-915, 2021. doi: 10.1158/2159-8290.cd-21-0090

2. A. Torkamannia, Y. Omidi, and R. Ferdousi, "A review of machine learning approaches for drug synergy prediction in cancer," Briefings in Bioinformatics, vol. 23, no. 3, 2022. doi: 10.1093/bib/bbac075

3. A. Partin, T. S. Brettin, Y. Zhu, O. Narykov, A. Clyde, J. Overbeek, and R. L. Stevens, "Deep learning methods for drug response prediction in cancer: Predominant and emerging trends," Frontiers in Medicine, vol. 10, p. 1086097, 2023. doi: 10.3389/fmed.2023.1086097

4. P. Symeonidis, S. Chairistanidis, and M. Zanker, "Deep reinforcement learning for medicine recommendation," In 2022 IEEE 22nd International Conference on Bioinformatics and Bioengineering (BIBE), November, 2022, pp. 85-90. doi: 10.1109/bibe55377.2022.00026

5. R. Qureshi, M. Irfan, T. M. Gondal, S. Khan, J. Wu, M. U. Hadi, and T. Alam, "AI in drug discovery and its clinical relevance," Heliyon, vol. 9, no. 7, 2023. doi: 10.1016/j. heliyon. 2023. e17575

6. H. Li, L. Zou, J. A. H. Kowah, D. He, Z. Liu, X. Ding, and X. Liu, "A compact review of progress and prospects of deep learning in drug discovery," Journal of Molecular Modeling, vol. 29, no. 4, p. 117, 2023. doi: 10.1007/s00894-023-05492-w

7. F. Boniolo, E. Dorigatti, A. J. Ohnmacht, D. Saur, B. Schubert, and M. P. Menden, "Artificial intelligence in early drug discovery enabling precision medicine," Expert Opinion on Drug Discovery, vol. 16, no. 9, pp. 991-1007, 2021. doi: 10.1080/17460441.2021.1918096

8. A. Waqas, A. Tripathi, R. P. Ramachandran, P. A. Stewart, and G. Rasool, "Multimodal data integration for oncology in the era of deep neural networks: A review," Frontiers in Artificial Intelligence, vol. 7, p. 1408843, 2024. doi: 10.3389/frai.2024.1408843

9. C. Sarkar, B. Das, V. S. Rawat, J. B. Wahlang, A. Nongpiur, I. Tiewsoh, and H. T. Sony, "Artificial intelligence and machine learning technology driven modern drug discovery and development," International Journal of Molecular Sciences, vol. 24, no. 3, p. 2026, 2023. doi: 10.3390/ijms24032026

10. W. Chen, X. Liu, S. Zhang, and S. Chen, "Artificial intelligence for drug discovery: Resources, methods, and applications," Molecular Therapy Nucleic Acids, vol. 31, pp. 691-702, 2023. doi: 10.1016/j.omtn.2023.02.019

11. J. Ghosh, and A. Roy, "Reframing cancer as an immunological disorder through personalized nutrition and AI integration," In AI-Assisted Computational Approaches for Immunological Disorders, 2025, pp. 323-352. doi: 10.4018/979-8-3693-9725-1.ch012

12. A. I. Visan, and I. Negut, "Integrating artificial intelligence for drug discovery in the context of revolutionizing drug delivery," Life, vol. 14, no. 2, p. 233, 2024. doi: 10.3390/life14020233

13. M. Chen, Y. Pan, X. Lei, C. Ji, Y. Dai, and Y. Pan, "MKMGCN-DDI: Predicting drug-drug interactions via magnetic graph convolutional network with multiple kernels," IEEE Transactions on Computational Biology and Bioinformatics, 2025. doi: 10.1109/tcbbio.2024.3502507

14. E. Streviniotis, N. Giatrakos, Y. Kotidis, T. Ntiniakou, and M. P. de Leon, "Optimizing resource allocation for tumor simulations over HPC infrastructures," In 2023 IEEE 10th International Conference on Data Science and Advanced Analytics (DSAA), October, 2023, pp. 1-10.

15. C. Shiranthika, K. W. Chen, C. Y. Wang, C. Y. Yang, B. H. Sudantha, and W. F. Li, "Supervised optimal chemotherapy regimen based on offline reinforcement learning," IEEE Journal of Biomedical and Health Informatics, vol. 26, no. 9, pp. 4763-4772, 2022.