Trusted Blockchain-Based Clinical Decision and Medication Management System for Movement Disorders
Centralized healthcare information systems face significant challenges related to security, interoperability, and real-time monitoring, particularly in the management of movement disorders. This paper proposes a novel blockchain-based framework that integrates wearable inertial measurement units (IMUs), AI-driven analytics, and the Hyperledger Fabric blockchain to enable secure, decentralized decision-making in the management of movement disorders. The system employs a voting-based consensus mechanism, where medication dosage recommendations proposed by an AI model are validated by clinicians, ensuring transparency and accountability in treatment decisions. Experimental evaluations demonstrate the framework’s scalability, achieving a throughput of 185 transactions per second (TPS) and reducing latency to 0.285 seconds under a 300 TPS load, using an 8-core CPU configuration. The proposed architecture guarantees 100% auditability and tamper-evident records, significantly improving the security and efficiency of clinical workflows. Notably, the system achieves a 96.3% reduction in latency and shows promising performance in both medication safety and treatment response times. The integration of blockchain and AI-based dosage recommendations offers a scalable and low-latency solution for remote patient monitoring and personalized healthcare management in patients with movement disorders. This work provides a practical solution to the challenges of decentralized decision-making and real-time data integration, offering a pathway to more resilient and secure healthcare systems.
Authors
- Mehdi Delrobaei (ORCID: https://orcid.org/0000-0002-4188-6958)
- Nima Afraz (ORCID: https://orcid.org/0000-0002-8422-9878)
- Behnaz Behara (ORCID: https://orcid.org/0000-0001-6153-1479)
Institutions
- University College Dublin (IE)
- K. N. Toosi University of Technology (IR)
Publication Details
- Journal
- IEEE Access
- Published
- 2025-01-01
- DOI
- https://doi.org/10.1109/access.2025.3596693
- Primary Topic
- Stroke Rehabilitation and Recovery
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Iran National Science Foundation