Personalized medicine seeks to provide patients with more personalized treatment options; however, determining the proper medication and its dose remains a challenging process. This research introduces an explainable framework for personalized medicine that employs patient-centric information to derive personalized drug and dose recommendations. This approach leverages RAG in conjunction with EHR data, machine learning models, and explainable AI methods to generate recommendations based on current and traceable medical evidence. Moreover, our framework uses the digital twin concept to create personalized patient representations and simulate possible outcomes of applying certain drugs and dosing options. In addition to generating the personalized drug recommendation, our framework also offers an explanation for why this drug and dose should be chosen. This approach is evaluated on the ADR-20K multicohort dataset comprising 20,030 de-identified patients belonging to Hypertension, Diabetes Mellitus, Oncology, and Renal Impairment cohorts. It found that this approach outperforms guideline-based approaches in terms of dose prediction, calibration, and adverse drug reaction discrimination.

References

[1] M. Pirmohamed, ―Pharmacogenomics: Current Status and Future Perspectives,‖ Nature Reviews Genetics, vol. 24, pp. 350–362, 2023.

[2] L. Amaro-Álvarez, J. Cordero-Ramos, and M. Á. Calleja-Hernández, ―Exploring the Impact of Pharmacogenetics on Personalized Medicine: A Systematic Review,‖ Farmacia Hospitalaria, vol. 48, no. 6, pp. 299–309, 2024.

[3] C. Xiao, E. Choi, and J. Sun, ―Opportunities and Challenges in Developing Deep Learning Models Using Electronic Health Records Data: A Systematic Review,‖ Journal of the American Medical Informatics Association, vol. 25, no. 10, pp. 1419–1428, 2018.

[4] A. S. Darwich et al., ―Model-Informed Precision Dosing: Background, Requirements, Validation, Implementation, and Forward Trajectory of Individualizing Drug Therapy,‖ Annual Review of Pharmacology and Toxicology, vol. 61, pp. 225–245, 2021.

[5] E. A. Poweleit, A. A. Vinks, and T. Mizuno, ―Artificial Intelligence and Machine Learning Approaches to Facilitate Therapeutic Drug Management and Model-Informed Precision Dosing,‖ Therapeutic Drug Monitoring, vol. 45, no. 2, pp. 143–150, 2023.

[6] H. W. Loh et al., ―Application of Explainable Artificial Intelligence for Healthcare: A Systematic Review of the Last Decade (2011–2022),‖ Computer Methods and Programs in Biomedicine, vol. 226,p.107161,2022.

[7] Q. Hu et al., ―Machine Learning to Predict Adverse Drug Events Based on Electronic Health Records: A Systematic Review and Meta-Analysis,‖ Journal of International Medical Research, vol. 52,no.12,2024.

[8] P. Lewis et al., ―Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,‖ Advances in Neural Information Processing Systems, vol. 33, 2020.

[9] R. Yang et al., ―Retrieval-Augmented Generation in Medicine: A Scoping Review of Technical Implementations, Clinical Applications, and Ethical Considerations,‖ Cell Reports Medicine, 2026, p. 102927.

[10] M. N. Kamel Boulos and P. Zhang, ―Digital Twins: From Personalised Medicine to Precision Public Health,‖ Journal of Personalized Medicine, vol. 11, no. 8, p. 745, 2021.

[11] S. Y. Saratkar et al., ―Digital Twin for Personalized Medicine Development,‖ Frontiers in Digital Health, vol. 7, p. 1583466, 2025.

[12] A. Mohan Babu and E. S. Madhan, ―Human Digital Twins in Personalized and Predictive Healthcare: A Comprehensive Review of Technologies, Applications, and Future Directions,‖ Frontiers in Digital Health, vol. 8, p. 1827007, 2026.

[13] M. Ghassemi et al., ―A Review of Challenges and Opportunities in Machine Learning for Health,‖ AMIA Joint Summits on Translational Science Proceedings, 2020.

[14] J. Jung, H. Lee, H. Jung, and H. Kim, ―Essential Properties and Explanation Effectiveness of Explainable Artificial Intelligence in Healthcare: A Systematic Review,‖ Heliyon, vol. 9, no. 5, e16110,2023.

[15] M. N. Kamel Boulos and P. Zhang, ―Digital Twins: From Personalised Medicine to Precision Public Health,‖ Journal of Personalized Medicine, vol. 11, no. 8, p. 745, 2021.

[16] P. Lewis et al., ―Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks,‖ Advances in Neural Information Processing Systems, vol. 33, pp. 9459–9474, 2020.

[17] M. Shen, S. Chen, and X. Ding, ―The Effectiveness of Digital Twins in Promoting Precision Health Across the Entire Population: A Systematic Review,‖ npj Digital Medicine, vol. 7, p. 145, 2024.

[18] E. A. Poweleit, A. A. Vinks, and T. Mizuno, ―Artificial Intelligence and Machine Learning Approaches to Facilitate Therapeutic Drug Management and Model-Informed Precision Dosing,‖ Therapeutic Drug Monitoring, vol. 45, no. 2, pp. 143–150, 2023.

[19]Q. Hu, J. Li, X. Li, D. Zou, T. Xu, and Z. He, ―Machine Learning to Predict Adverse Drug Events Based on Electronic Health Records: A Systematic Review and Meta-Analysis,‖ International Journal of Medical Sciences, vol. 52, no. 12, 2024.

[20] Q. Hu, Y. Chen, D. Zou, Z. He, and T. Xu, ―Predicting Adverse Drug Event Using Machine Learning Based on Electronic Health Records: A Systematic Review and Meta-Analysis,‖ Frontiers in Pharmacology, vol. 15, p. 1497397, 2024.