Blockchain-Based IoMT Security: BSHS-EODL Method for Secure Data Storage and Analysis

Abstract
The integration of the Internet of Medical Things (IoMT) has revolutionized healthcare by improving patient care and system efficiency. However, this progress introduces significant concerns about data security and privacy, particularly with medical data. Traditional methods like Decision Tree, Random Forest, and Naïve Bayes face limitations in scalability, accuracy for large datasets, and energy efficiency. To address these challenges, this research introduces a novel Blockchain-based IoMT framework, BSHS-EODL (Blockchain-Secured Healthcare System with Edge-Oriented Deep Learning). The framework employs Long Short-Term Memory (LSTM) networks for precise healthcare data analysis, optimized using the Grey Wolf Optimization (GWO) algorithm for hyperparameter tuning. The proposed system achieved outstanding results, including an accuracy of 99.42%, precision of 99.51%, recall rate of 99.47%, and F1 score of 99.39%, outperforming conventional methods. Moreover, BSHS-EODL demonstrated remarkable efficiency, this approach not only enhances healthcare data security and diagnostic accuracy The system is implemented using Python integrated with MATLAB.

Author
Mustafa Zuhaer Nayef Al-Dabagh

DOI
https://doi.org/10.1109/ICICACS65178.2025.10967784

Publisher

ISSN

Publish Date: