Secure internet of medical things based electronic health records scheme in trust decentralized loop federated learning consensus blockchain

Abstract

Electronic Health Records (EHRs) have become an increasingly significant source of information for healthcare professionals and researchers. Two technical challenges are addressed: motivating federated learning members to contribute their time and effort, and ensuring accurate aggregation of the global model by the centralized federated learning server. To overcome these issues and establish a decentralized solution, the integration of blockchain and federated learning proves effective, offering enhanced security and privacy for smart healthcare. The proposed approach includes a gamified element to incentivize and recognize contributions from federated learning members. This research work offers a solution involving resource management within the Internet of Medical Things (IoMT) using a newly proposed trust decentralized loop federated learning consensus blockchain. The obtained raw data is pre-processed by using handling missing values and adaptive min-max normalization. The appropriate features are selected with the aid of hybrid weighted-leader exponential distribution optimization algorithm. Because, data with multiple features exhibits varying levels of variation across each feature. The selected features are then forwarded to the training phase through the proposed pyramid squeeze attention generative adversarial networks to classify the EHR as positive and negative. The proposed classification model demonstrates high flexibility and scalability, making it applicable to a wide range of network architectures for various computer vision tasks. The introduced model provides better outcomes in terms of 98.5% in the training accuracy and 99% in the validation accuracy over Medical Information Mart for Intensive Care III (MIMIC-III) dataset, which is more efficient than the other traditional methods.