MedTrace: A Privacy-Preserving Federated Learning Framework For Clinical Drug Interaction Monitoring

Author

Reena Satpute, Ananya Lokhande, Shravani Pimpale, Anushri Mahajan, Gopal Padalkar, Rohit Jumnake

Abstract

 Drug-drug interactions (DDIs) are a significant concern in healthcare, particularly when patients are prescribed multiple medicines at the same time. One drug can change the effect of another, which may lead to adverse effects, reduced treatment effectiveness, or other unexpected outcomes. Machine learning can help identify such interactions, but many conventional approaches depend on collecting healthcare data in a central location. This is difficult in practice because clinical records contain sensitive patient and institutional information and cannot always be freely shared. To address this issue, this paper proposes MedTrace, a privacy-preserving framework for clinical drug interaction monitoring using Federated Learning (FL). In MedTrace, participating healthcare institutions keep their data locally and train the model on their own datasets. Instead of sending patient records to a central server, they share only the model updates required for collaborative training. The federated server combines these updates to create a global model and sends the improved model back to the participating clients. The application layer uses Python and Django, while Flower can be used to manage the federated learning process. The aim of MedTrace is to support the identification of possible drug interactions and medication-related anomalies without requiring institutions to give up control of their clinical data. By bringing together federated learning, clinical monitoring, and a web-based interface, the framework provides a practical starting point for privacy-aware healthcare analytics.

Keywords

Federated Learning, Drug-Drug Interaction, Healthcare, Privacy-Preserving Machine Learning, Anomaly Detection, Django, Python, Clinical Decision Support.

Full Text:

Download Paper PDF

References

[1]T. Li, A. K. Sahu, A. Talwalkar, and V. Smith, “Federated learning: Challenges, methods, and future directions,” IEEE Signal Processing Magazine, vol. 37, no. 3, pp. 50–60, May 2020, doi: 10.1109/MSP.2020.2975749.
[2]W. Y. B. Lim, N. C. Luong, D. T. Hoang, Y. Jiao, Y.-C. Liang, Q. Yang, D. Niyato, and C. Miao, “Federated learning in mobile edge networks: A comprehensive survey,” IEEE Communications Surveys & Tutorials, vol. 22, no. 3, pp. 2031–2063, 2020, doi: 10.1109/COMST.2020.2986024.
[3]N. Rieke et al., “The future of digital health with federated learning,” npj Digital Medicine, vol. 3, Art. no. 119, 2020, doi: 10.1038/s41746-020-00323-1.
[4]M. J. Sheller et al., “Federated learning in medicine: Facilitating multi-institutional collaborations without sharing patient data,” Scientific Reports, vol. 10, Art. no. 12598, 2020, doi: 10.1038/s41598-020-69250-1.
[5]A. Sadilek et al., “Privacy-first health research with federated learning,” npj Digital Medicine, vol. 4, Art. no. 132, 2021, doi: 10.1038/s41746-021-00489-2.
[6] M. Ali, F. Naeem, M. Tariq, and G. Kaddoum, “Federated learning for privacy preservation in smart healthcare systems: A comprehensive survey,” IEEE Journal of Biomedical and Health Informatics, vol. 27, no. 2, pp. 778–789, Feb. 2023, doi: 10.1109/JBHI.2022.3181823.
[7] V. A. Patel, P. Bhattacharya, S. Tanwar, R. Gupta, G. Sharma, P. N. Bokoro, and R. Sharma, “Adoption of federated learning for healthcare informatics: Emerging applications and future directions,” IEEE Access, vol. 10, pp. 90792–90826, 2022, doi: 10.1109/ACCESS.2022.3201876.
[8] Z. K. Taha, C. T. Yaw, S. P. Koh, S. K. Tiong, K. Kadirgama, F. Benedict, J.-D. Tan, and Y. Balasubramaniam, “A survey of federated learning from data perspective in the healthcare domain: Challenges, methods, and future directions,” IEEE Access, vol. 11, pp. 45711–45735, 2023, doi: 10.1109/ACCESS.2023.3267964.
[9] M. Abaoud, M. A. Almuqrin, and M. F. Khan, “Advancing federated learning through novel mechanism for privacy preservation in healthcare applications,” IEEE Access, vol. 11, pp. 83562–83579, 2023, doi: 10.1109/ACCESS.2023.3301162.
[10] M. F. Khan and M. Abaoud, “Blockchain-integrated security for real-time patient monitoring in the Internet of Medical Things using federated learning,” IEEE Access, vol. 11, pp. 117826–117850, 2023, doi: 10.1109/ACCESS.2023.3326155.
[11] M. C. Tedeschini, S. Savazzi, R. Stoklasa, L. Barbieri, I. Stathopoulos, M. Nicoli, and L. Serio, “Decentralized federated learning for healthcare networks: A case study on tumor segmentation,” IEEE Access, vol. 10, pp. 8693–8708, 2022, doi: 10.1109/ACCESS.2022.3141913.
[12] M. F. Sohan and A. Basalamah, “A systematic review on federated learning in medical image analysis,” IEEE Access, vol. 11, pp. 28628–28644, 2023, doi: 10.1109/ACCESS.2023.3260027.
[13] S. H. Moon and W. H. Lee, “Privacy-preserving federated learning in healthcare,” in Proc. 2023 International Conference on Electronics, Information, and Communication (ICEIC), 2023, doi: 10.1109/ICEIC57457.2023.10049966.
[14] M. J. Ali et al., “Privacy-preserving federated learning with domain adaptation for multi-disease ocular disease recognition,” IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 6, pp. 3219–3227, 2024, doi: 10.1109/JBHI.2023.3305685.
[15] A. Padmavathi, N. Kushwaha, and S. Varma, “A privacy-preserving federated learning framework for adaptable cross-organizational collaboration,” in Proc. 2026 IEEE International Conference on AI Engineering and Innovations (AIEI), 2026, doi: 10.1109/AIEI69164.2026.11497944.
[16] A. Shrivastava, H. M. Al-Jawahry, A. Kumar, and K. S. Kumar, “Federated foundation models for privacy-preserving multi-modal healthcare diagnostics,” in Proc. 2026 Contemporary Computing Innovations Conference (CCIC), 2026, doi: 10.1109/CCIC68129.2026.11486249.
[17] G. Hernandez-Penaloza, S. Uribe, F. Moreno, B. Arroyo, and F. Alvarez, “Federated learning and medical device regulation: Bridging gaps in healthcare AI governance,” in Proc. 2025 IEEE International Conference on E-health Networking, Application & Services (Healthcom), 2025, pp. 25–31, doi: 10.1109/HealthCom60686.2025.11342827.
[18] P. K. Shukla, P. Sharma, P. Rawat, J. Samar, R. Moriwal, and M. Kaur, “Efficient prediction of drug-drug interaction using deep learning models,” IET Systems Biology, vol. 14, no. 4, pp. 211–216, 2020, doi: 10.1049/iet-syb.2019.0116.
[19] M. Wang, H. Wang, X. Liu, and X. Ma, “Drug-drug interaction predictions via knowledge graph and text embedding: Instrument validation study,” JMIR Medical Informatics, vol. 9, no. 6, Art. no. e28277, 2021, doi: 10.2196/28277.
[20] A. K. Nyamabo, H. Yu, J.-Y. Shi, and Z. Liu, “SSI-DDI: Substructure-substructure interactions for drug-drug interaction prediction,” Briefings in Bioinformatics, vol. 22, no. 6, 2021, doi: 10.1093/bib/bbab133.
[21] A. K. Nyamabo, H. Yu, Z. Liu, and J.-Y. Shi, “Drug-drug interaction prediction with learnable size-adaptive molecular substructures,” Briefings in Bioinformatics, vol. 23, no. 1, 2022, doi: 10.1093/bib/bbab441.
[22] M. H. Al-Rabeah and A. Lakizadeh, “Prediction of drug-drug interaction events using graph neural networks based feature extraction,” Scientific Reports, vol. 12, Art. no. 15590, 2022, doi: 10.1038/s41598-022-19999-4.
[23] S. Liu, Y. Zhang, Y. Cui, Y. Qiu, Y. Deng, Z. Zhang, and W. Zhang, “Enhancing drug-drug interaction prediction using deep attention neural networks,” IEEE/ACM Transactions on Computational Biology and Bioinformatics, vol. 20, no. 2, pp. 976–985, 2023, doi: 10.1109/TCBB.2022.3172421.
[24] F. Tanvir, K. M. Saifuddin, M. I. K. Islam, and E. Akbas, “Predicting drug-drug interactions using heterogeneous graph attention networks,” in Proc. 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 2023, Art. no. 48, pp. 1–6, doi: 10.1145/3584371.3613065.
[25] Y. Zhao, J. Yin, L. Zhang, Y. Zhang, and X. Chen, “Drug-drug interaction prediction: Databases, web servers and computational models,” Briefings in Bioinformatics, vol. 25, no. 1, Art. no. bbad445, 2024, doi: 10.1093/bib/bbad445.
[26] H. Luo, W. Yin, J. Wang, G. Zhang, et al., “Drug-drug interactions prediction based on deep learning and knowledge graph: A review,” iScience, vol. 27, no. 3, Art. no. 109148, 2024, doi: 10.1016/j.isci.2024.109148.
[27] Y. Wang, Z. Yang, and Q. Yao, “Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning,” Communications Medicine, vol. 4, Art. no. 59, 2024, doi: 10.1038/s43856-024-00486-y.
[28] F.-I. Gheorghita, V.-I. Bocanet, and L. B. Iantovics, “Machine learning-based drug-drug interaction prediction: A critical review of models, limitations, and data challenges,” Frontiers in Pharmacology, vol. 16, Art. no. 1632775, 2025, doi: 10.3389/fphar.2025.1632775.
[29] W. Zhang, P. Peissig, Z. Kuang, and D. Page, “Adverse drug reaction discovery from electronic health records with deep neural networks,” in Proc. ACM Conference on Health, Inference, and Learning, 2020, pp. 30–39, doi: 10.1145/3368555.3384459.
[30] C. Y. Lee and Y.-P. P. Chen, “Prediction of drug adverse events using deep learning in pharmaceutical discovery,” Briefings in Bioinformatics, vol. 22, no. 2, pp. 1884–1901, 2021, doi: 10.1093/bib/bbaa040.

Share your valuable work from Social Media Buttons