Machine Learning Framework for Privacy-preserving Smart Healthcare in Rural India
Keywords:
Client selection, Communication compression, Federated learning, Internet of Medical Things (IoMT), Low-bandwidth systems, Privacy-preserving machine learning, Rényi differential privacy, Rural healthcare, Secure aggregationAbstract
The study proposes a machine learning framework for privacy-preserving smart healthcare, tailored to the constraints and needs of rural India. The framework combines edge-side federated learning, per-round differential privacy, and lightweight on-device inference to enable collaborative model training without transferring raw patient data from Primary Health Centers (PHCs) and Community Health Workers (CHWs). To accommodate intermittent connectivity and low-bandwidth conditions common in rural deployments, the design incorporates explicit client selection policies, asynchronous update aggregation, communication compression (sparsification and quantization), and opportunistic synchronization. The system supports heterogeneous data sources (wearables, low-cost sensors, portable imaging devices, and structured clinical records) and provides modular risk controls including local model validation, secure aggregation, policy-driven data minimization, and an auditable privacy_log. A layered privacy strategy—data minimization at capture, local preprocessing, per-round DP noise injection with gradient clipping, Rényi Differential Privacy (RDP) accounting, and encrypted aggregation—balances utility and privacy while aligning with emerging Indian regulatory expectations. We evaluate the framework conceptually and experimentally using representative use-cases (maternal-child monitoring, chronic disease screening), and present analyses of privacy budget consumption (ε progression), communication vs. convergence trade-offs (sparsification vs. rounds-to-convergence), and threat models (honest-but-curious server, model inversion). Results obtained via literature-grounded parameter choices and targeted simulations indicate the framework can achieve high utility with provable privacy guarantees and operational feasibility in low-resource settings. We conclude with deployment guidelines and a research roadmap for field trials, including concrete metrics for privacy–utility trade-offs, connectivity-resilience, and socio-ethical acceptance.
References
A. Rahman et al., “Machine learning and deep learning-based approach in smart healthcare: Recent advances, applications, challenges and opportunities,” AIMS Public Health, vol. 11, no. 1, pp. 58–109, Jan. 2024, doi: https://doi.org/10.3934/publichealth.2024004
N. Jain, M. N. Meqdad, V. K. Chaurasiya, D. Bhardwaj, A. K. Rao, N. Kumar, A. Deepak, and A. Shrivastava, “Scalable machine learning framework for patient outcome prediction with cloud-based healthcare data,” International Journal of Intelligent Systems and Applications in Engineering, vol. 12, no. 20s, pp. 92–99, 2024, Available: https://ijisae.org/index.php/IJISAE/article/view/5121
M. Paul, L. Maglaras, M. A. Ferrag, and I. Almomani, “Digitization of healthcare sector: A study on privacy and security concerns,” ICT Express, vol. 9, no. 4, pp. 571–588, 2023, doi: https://doi.org/10.1016/j.icte.2023.02.007
A. Adnan, F. Kausar, M. Shoaib, F. Iqbal, A. Altaf, and H. M. Asif, “A secure and privacy-preserving approach to healthcare data collaboration,” Symmetry, vol. 17, no. 7, p. 1139, 2025, doi: https://doi.org/10.3390/sym17071139
E. A. Mantey et al., “Federated learning approach for secured medical recommendation in internet of medical things using homomorphic encryption,” in IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 6, pp. 3329–3340, June 2024, doi: https://doi.org/10.1109/JBHI.2024.3350232
B. Wang, H. Li, Y. Guo, and J. Wang, “PPFLHE: A privacy-preserving federated learning scheme with homomorphic encryption for healthcare data,” Applied Soft Computing, vol. 146, p. 110677, 2023, doi: https://doi.org/10.1016/j.asoc.2023.110677
F. Wang et al., “Privacy-preserving collaborative model learning scheme for e-healthcare,” in IEEE Access, vol. 7, pp. 166054-166065, 2019, doi: https://doi.org/10.1109/ACCESS.2019.2953495
N. M. Hijazi, M. Aloqaily, M. Guizani, B. Ouni and F. Karray, “Secure federated learning with fully homomorphic encryption for IoT communications,” in IEEE Internet of Things Journal, vol. 11, no. 3, pp. 4289–4300, Feb. 2024, doi: https://doi.org//10.1109/JIOT.2023.3302065
X. Gu, F. Sabrina, Z. Fan, and S. Sohail, “A review of privacy enhancement methods for federated learning in healthcare systems,” International Journal of Environmental Research and Public Health, vol. 20, no. 15, p. 6539, Jan. 2023, doi: https://doi.org/10.3390/ijerph20156539
R. S. Antunes, C. André da Costa, A. Küderle, I. A. Yari, and B. Eskofier, “Federated learning for healthcare: Systematic review and architecture proposal,” ACM Transactions on Intelligent Systems and Technology, vol. 13, no. 4, pp. 1–23, Aug. 2022, doi: https://doi.org/10.1145/3501813
Y. Zhou, Q. Ye and J. Lv, “Communication-efficient federated learning with compensated overlap-FedAvg,” in IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 1, pp. 192–205, Jan. 2022, doi: https://doi.org/10.1109/TPDS.2021.3090331
C. Xu, N. Wang, L. Zhu, K. Sharif and C. Zhang, “Achieving searchable and privacy-preserving data sharing for cloud-assisted e-healthcare system,” in IEEE Internet of Things Journal, vol. 6, no. 5, pp. 8345–8356, Oct. 2019, doi: https://doi.org/10.1109/JIOT.2019.2917186
N. Khalid, A. Qayyum, M. Bilal, A. Al-Fuqaha, and J. Qadir, “Privacy-preserving artificial intelligence in healthcare: Techniques and applications,” Computers in Biology and Medicine, vol. 158, no. 1, p. 106848, Apr. 2023, doi: https://doi.org/10.1016/j.compbiomed.2023.106848
W. Liu, T. Zhou, L. Chen, H. Yang, J. Han, and X. Yang, “Round efficient privacy-preserving federated learning based on MKFHE,” Computer standards & interfaces, vol. 87, pp. 103773–103773, Jan. 2024, doi: https://doi.org/10.1016/j.csi.2023.103773
L. Zhang, J. Xu, P. Vijayakumar, P. K. Sharma and U. Ghosh, “Homomorphic encryption-based privacy-preserving federated learning in IoT-enabled healthcare system,” in IEEE Transactions on Network Science and Engineering, vol. 10, no. 5, pp. 2864–2880, Sept.–Oct. 2023, doi: https://doi.org/10.1109/tnse.2022.3185327
V. R. Parihar, S. A. Chaturvedi, “An adaptive machine learning based framework for autonomous drone navigation”, International Conference on Recent Trends and Research in Engineering & Science (ICRTRES 2K25), vol. 10, no. 1 May 2025, Available: https://zenodo.org/records/16314432
V. R. Parihar and S. A. Chaturvedi, “AirSim-based evaluation of deep q-networks for autonomous UAV navigation in dynamic environments,” Journal of Instrumentation and Innovation Sciences, vol. 10, no. 2, 2025, Available: https://matjournals.net/engineering/index.php/JIIS/article/view/2265
A. Qayyum, K. Ahmad, M. A. Ahsan, A. Al-Fuqaha, and J. Qadir, “Collaborative federated learning for healthcare: Multi-modal COVID-19 diagnosis at the edge,” IEEE Open Journal of the Computer Society, vol. 3, pp. 172–184, 2022, doi: https://doi.org/10.1109/ojcs.2022.3206407
S. Singh, S. Rathore, O. Alfarraj, A. Tolba, and B. Yoon, “A framework for privacy-preservation of IoT healthcare data using Federated Learning and blockchain technology,” Future Generation Computer Systems, vol. 129, pp. 380–388, Apr. 2022, doi: https://doi.org/10.1016/j.future.2021.11.028
F. Kausar, Rami Al-Hamouz, and S. Hussain, “Energy demand forecasting for electric vehicles using blockchain-based Federated Learning,” IEEE Access, vol. 12, pp. 41287–41298, Jan. 2024, doi: https://doi.org/10.1109/access.2024.3377661
R. Haripriya, N. Khare, M. Pandey, and S. Biswas, “A privacy-enhanced framework for collaborative Big Data analysis in healthcare using adaptive federated learning aggregation,” Journal of Big Data, vol. 12, no. 1, May 2025, doi: https://doi.org/10.1186/s40537-025-01169-8
