Cutting-edge optimized multi-source data fusion for trusted execution and management of blockchain transactions on the internet of medical things (IoMT) with machine learning.

A modernized healthcare environment is possibly fuelled by the collaborative nature of Blockchain Technology (BT) and the Internet of Medical Things (IoMT), which guarantees efficient management, scalability, ledger optimization, and security. However, the huge volume of data created and the heterogeneous potential of IoMT devices make it difficult to achieve trustworthy execution as well as effective transaction management and organization. Using cutting-edge Machine Learning (ML) algorithms, like Lightweight Artificial Neural Networks (LANNs) with BT, this paper proposes an optimised multi-source data fusion framework that improves data integrity, real-time decision-making, efficiency, and scalability in an IoMT application environment. In order to assure accuracy and relevance, the data fusion mechanism merges multi-modal data from several IoMT devices. This enables the application of advanced fusion techniques, including Kalman Filtering enabled feature extraction. This guarantees the blockchain network processes only high-quality, pre-validated data. In addition, for secure transaction processing, the proposed architecture includes a trusted execution environment, guaranteeing data privacy and reliability. The proposed solution is good for resource-constrained IoMT contexts since it uses a hybrid consensus mechanism and clever data aggregation to reduce latency and computational cost. Comparing experimental results to classical blockchain-IoMT techniques, data accuracy, transaction throughput, and application security all show notable improvements of up to 98.33%, 97.98%, and 2.34%, respectively. Through the resolution of significant implementation constraints in blockchain transaction management and multi-source data fusion, this research offers a solid approach for developing IoMT ecosystems.