Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206199,
        author = {S. SENTHAMARAI and Dr.R.. MALA},
        title = {Enhanced Privacy-Preserving Blockchain-Enabled Federated Learning (EPP-BCFL) for Secure Healthcare Intelligence},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {532-540},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206199},
        abstract = {The rapid integration of Artificial Intelligence (AI), the Internet of Medical Things (IoMT), and Electronic Health Records (EHRs) has substantially transformed modern healthcare by enabling intelligent disease diagnosis, remote patient monitoring, and personalized clinical treatment. However, conventional centralized machine learning approaches require healthcare institutions to transmit sensitive patient data to centralized servers, thereby raising serious privacy, security, and regulatory concerns. Federated Learning (FL) has emerged as a promising distributed learning paradigm that facilitates collaborative model training without direct exchange of raw patient data. Despite these advantages, existing FL frameworks remain susceptible to model poisoning attacks, excessive communication overhead, insufficient trust management mechanisms, and malicious participant behavior.
To address these persistent limitations, this paper proposes an Enhanced Privacy-Preserving Blockchain-Enabled Federated Learning (EPP-BCFL) framework designed for secure healthcare intelligence. The proposed architecture seamlessly integrates federated learning with blockchain technology through a lightweight Proof-of-Stake Byzantine Fault Tolerant (PoS-BFT) consensus mechanism, achieving improved trust, scalability, communication efficiency, and robustness against adversarial attacks. Smart contracts are employed to validate encrypted model updates, while secure aggregation protocols safeguard sensitive healthcare information throughout the collaborative training process. The proposed EPP-BCFL framework was rigorously evaluated using three real-world healthcare datasets: the MIMIC-III clinical database, the Breast Cancer Wisconsin Diagnostic Dataset, and the ChestX-ray14 medical imaging dataset. Experimental results demonstrate that the proposed framework achieves 95.2% classification accuracy, reduced communication overhead, enhanced privacy preservation, low blockchain validation latency, and strong resilience against adversarial attacks when compared with existing federated learning approaches.},
        keywords = {Federated Learning, Blockchain, Healthcare Intelligence, Privacy Preservation, Electronic Health Records, IoMT, Smart Contracts, PoS-BFT, Deep Learning, Secure Healthcare Analytics.},
        month = {July},
        }