PABFL: Secure and Privacy-Aware Framework for Electronic Health Record Sharing in IoMT
Abstract
The fast development of Internet of Medical Things (IoMT) devices has also compounded the necessity to have secure, privacy-sensitive, and efficient Electronic Health Record (EHR) sharing mechanisms. To overcome the fundamental issues associated with the IoMT ecosystems of data privacy leakage, excessive communication overhead, and inefficient decentralized learning, this paper suggests a Privacy-Aware Blockchain and Federated Learning (PABFL) system. The suggested framework combines a blockchain-based secure data sharing with federated learning-based distributed model training, which guarantees data confidentiality and integrity without the centralized storage. It is tested with NVIDIA Jetson AGX Xavier nodes, which have CUDA 11.4 acceleration and is tested on both CardioFit and GlucoWatch datasets. Through experiments, it is shown that PABFL greatly outperforms more traditional methods like Federated Averaging (FedAvg), Federated Proximal (FedProx), and Asynchronous Advantage Actor-Critic (A3C) with an accuracy difference of 6.8%-9.5%, energy consumption of 18.2%-24.7%, training time of 21.4%-29.3% These improvements are explained by optimized model aggregation, safe lightweight blockchain operations, and resource-efficient edge device utilization. The suggested framework provides high-quality, scalable, and privacy-friendly EHR sharing that is very appropriate in real-time healthcare applications in IoMT settings and helps to develop safe and smart digital healthcare systems.