IRO Journals
Journal of Ubiquitous Computing and Communication Technologies

Privacy-Aware Retrieval-Augmented Generation for Intelligent IoMT Healthcare Systems

Open Access
Published: 17 June, 2026
Pages: 177-197
  • Manas Kumar Yogi , Manas Kumar Yogi
    Department of Computer Science and Engineering, Pragati Engineering College, Surampalem, Andhra Pradesh, India
    Department of Computer Science and Engineering, Pragati Engineering College, Surampalem, Andhra Pradesh, India
  • Dhanushya Donga Dhanushya Donga
    Department of Computer Science and Engineering, Pragati Engineering College, Surampalem, Andhra Pradesh, India
    Department of Computer Science and Engineering, Pragati Engineering College, Surampalem, Andhra Pradesh, India
view PDF
view PDF

How to Cite

Yogi, Manas Kumar, and Dhanushya Donga. 2026. “Privacy-Aware Retrieval-Augmented Generation for Intelligent IoMT Healthcare Systems”. Journal of Ubiquitous Computing and Communication Technologies 8 (3): 177-97. https://doi.org/10.36548/jucct.2026.3.002.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

Internet of Medical Things
Privacy Preservation Techniques
Retrieval-Augmented Generation
Secure Data Processing
Smart Healthcare Systems

Abstract

The Internet of Medical Things (IoMT) has brought about significant progress in real-time monitoring and AI-assisted decisions, there is an emerging need for overcoming some of the associated drawbacks such as fragmentation of health records and privacy concerns. This paper proposes the Privacy-Aware Retrieval-Augmented Generation (PA-RAG-IoMT) framework, which combines Large Language Models (LLMs) with privacy-aware medical knowledge retrieval. In particular, this approach utilizes the differential privacy technique known as (ε, δ)-DP in the process of retrieval and embedding extraction. A federated edge computing layer further ensures efficient data preprocessing and anonymization. In terms of security, the proposed solution features role-based access control (RBAC), AES-256 encryption, as well as adversarial input filtering. The impact of each of the components is estimated using ablation experiments, while the superiority in performance over other privacy-preserving benchmarks such as FedRAG and DP-BERT is confirmed statistically. According to the results obtained, the PA-RAG-IoMT framework provides 93.1% accuracy, 90.8% F1-score, and an AUC-ROC of 0.963 while hallucination rate decreased by 72.4%. The framework provides a sufficiently low level of latency required for the timely generation of clinical data, ensuring at least 88% utility at ε = 1.0 and thus complying with HIPAA and GDPR standards.

References

  1. Ahmed, Imran, Gwanggil Jeon, and Francesco Piccialli. "From Artificial Intelligence to Explainable Artificial Intelligence in Industry 4.0: A Survey on What, How, and Where." IEEE transactions on industrial informatics 2022, vol. 18, no. 8: 5031-5042.
  2. Al-Garadi, Mohammed Ali, Amr Mohamed, Abdulla Khalid Al-Ali, Xiaojiang Du, Ihsan Ali, and Mohsen Guizani. "A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Security." IEEE communications surveys & tutorials 2020, vol. 22, no. 3: 1646-1685.
  3. Antunes, Rodolfo Stoffel, Cristiano André da Costa, Arne Küderle, Imrana Abdullahi Yari, and Björn Eskofier. "Federated Learning for Healthcare: Systematic Review and Architecture Proposal." ACM Transactions on Intelligent Systems and Technology (TIST) 2022, vol. 13, no. 4: 1-23.
  4. Zhang, Haijun, Fang Fang, Julian Cheng, Keping Long, Wei Wang, and Victor CM Leung. "Energy-Efficient Resource Allocation in NOMA Heterogeneous Networks." IEEE Wireless Communications 2018, vol. 25, no. 2: 48-53.
  5. Zhu, Yanming, Xuefei Yin, Alan Wee-Chung Liew, and Hui Tian. "Privacy-Preserving in Medical Image Analysis: A Review of Methods and Applications." In International Conference on Parallel and Distributed Computing: Applications and Technologies 2024, Singapore: Springer Nature Singapore, 166-178.
  6. Beltagy, Iz, Kyle Lo, and Arman Cohan. "SciBERT: A Pretrained Language Model for Scientific Text." In Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing (EMNLP-IJCNLP) 2019, 3615-3620.
  7. Bonomi, Luca, Yingxiang Huang, and Lucila Ohno-Machado. "Privacy Challenges and Research Opportunities for Genomic Data Sharing." Nature genetics 2020, vol. 52, no. 7: 646-654.
  8. Dang, L. Minh, Md Jalil Piran, Dongil Han, Kyungbok Min, and Hyeonjoon Moon. "A Survey on Internet of Things and Cloud Computing for Healthcare." Electronics 2019, vol. 8, no. 7: 768.
  9. Dayan, Ittai, Holger R. Roth, Aoxiao Zhong, Ahmed Harouni, Amilcare Gentili, Anas Z. Abidin, Andrew Liu et al. "Federated Learning for Predicting Clinical Outcomes in Patients with COVID-19." Nature medicine 2021, vol. 27, no. 10: 1735-1743.
  10. Tang, Tingting, James Flemings, Yongqin Wang, and Murali Annavaram. "Differentially Private Retrieval-Augmented Generation." arXiv preprint arXiv:2602.14374 (2026).
  11. Moqurrab, Syed Atif, Noshina Tariq, Adeel Anjum, Alia Asheralieva, Saif UR Malik, Hassan Malik, Haris Pervaiz, and Sukhpal Singh Gill. "A Deep Learning-Based Privacy-Preserving Model for Smart Healthcare in Internet of Medical Things Using Fog Computing." Wireless Personal Communications 2022, vol. 126, no. 3: 2379.
  12. Wang, Benyou, Qianqian Xie, Jiahuan Pei, Zhihong Chen, Prayag Tiwari, Zhao Li, and Jie Fu. "Pre-Trained Language Models in Biomedical Domain: A Systematic Survey." ACM Computing Surveys 2023, vol. 56, no. 3: 1-52.
  13. Islam, SM Riazul, Daehan Kwak, MD Humaun Kabir, Mahmud Hossain, and Kyung-Sup Kwak. "The Internet of Things for Health Care: A Comprehensive Survey." IEEE access 2015, vol. 3: 678-708.
  14. Kaissis, Georgios A., Marcus R. Makowski, Daniel Rückert, and Rickmer F. Braren. "Secure, Privacy-Preserving and Federated Machine Learning in Medical Imaging." Nature Machine Intelligence 2020, vol. 2, no. 6: 305-311.
  15. Keshta, Ismail, and Ammar Odeh. "Security and Privacy of Electronic Health Records: Concerns and Challenges." Egyptian Informatics Journal 2021, vol. 22, no. 2: 177-183.
  16. Zhang, Zhuosheng, Jiarui Li, Shucheng Yu, and Christian Makaya. "SAFELearning: Secure Aggregation in Federated Learning with Backdoor Detectability." IEEE Transactions on Information Forensics and Security 2023, vol. 18: 3289-3304.
  17. Mohammadi, Marziyeh, Mohsen Vejdanihemmat, Mahshad Lotfinia, Mirabela Rusu, Daniel Truhn, Andreas Maier, and Soroosh Tayebi Arasteh. "Differential Privacy for Medical Deep Learning: Methods, Tradeoffs, And Deployment Implications." npj Digital Medicine 2026, vol. 9, no. 93.