A Novel Privacy Protection Technique of Electronic Health Records using Decentralized Federated Learning with Consortium Blockchain

Abstract

This research study proposes a novel FedBlock model by integrating the federated learning and blockchain technologies to enhance data security and predictive accuracy in healthcare domain. Across diverse medical datasets with varying data distributions, the proposed model outperforms existing methods in preserving data privacy and maintaining high predictive accuracy. By integrating federated learning, FedBlock achieves superior AUROC scores compared to blockchain-based and ShareChain models, showcasing its effectiveness in data privacy preservation. Additionally, the proposed model demonstrates a comparatively higher F1-score and accuracy rate with AUROC score reaching up to 0.98 while processing the medical dataset. Through collaborative training and decentralized data management, FedBlock ensures progressive accuracy improvements while safeguarding data integrity, paving way for enhanced healthcare data security and predictive analytics.