Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks

Authors

Mazin Abed Mohammed, Department of Artificial Intelligence, College of Computer Science and Information Technology, University of Anbar, Anbar 31001, IraqFollow
Mohd Khanapi Abd Ghani, Department of Software Engineering, Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia
Israa Badr Al-Mashhadani, Department of Computer Engineering, Al-Nahrain University, Baghdad 10072, Iraq
Sajida Memon, Department of Computer Science, Dawood University of Engineering and Technology, 74800, Sindh, Karachi, Pakistan
Sajida Memon, Department of Computer Science, Dawood University of Engineering and Technology, 74800, Sindh, Karachi, Pakistan
Haydar Abdulameer Marhoon, College of Computer Science and Information Technology, University of Kerbala, Karbala, Iraq
Marwan Ali Albahar, Department of Computing, College of Engineering and Computing in Al-Lith, Umm Al-Qura University, Makkah, Saudi Arabia

Document Type

Article

Keywords

Blockchain, Edge-Cloud, Healthcare Data Analytics, Federated Learning, Deep Neural Networks

Abstract

The exponential growth of healthcare Internet of Things (IoT) data necessitates secure, low-latency analytics that extend beyond centralized architectures. This paper presents BDAFL DNN, a blockchain-integrated data analytics framework that combines Federated Learning (FL) and Deep Neural Networks (DNNs) for real-time, privacy-preserving healthcare analytics across edge and cloud resources. Local devices such as smartwatches and phones collect noninvasive time series sensor streams (heart rate, temperature, and abdomen sensors), perform on device DNN training, and send only model updates to healthcare edge nodes, where a blockchain ledger validates updates for integrity and traceability; validated updates are then aggregated in the cloud via FL to produce a global model without sharing raw data. In a simulation study against representative baselines, BDAFL DNN reduced execution time, energy use, and resource consumption, lowered the deadline miss ratio, and improved blockchain validation correctness. These results show that integrating blockchain with FL-driven edge and cloud DNN analytics can deliver scalable, secure, and timely insights for future healthcare IoT systems.

How to Cite This Article

Mohammed, Mazin Abed; Ghani, Mohd Khanapi Abd; Al-Mashhadani, Israa Badr; Memon, Sajida; Memon, Sajida; Marhoon, Haydar Abdulameer; and Albahar, Marwan Ali (2025) "Blockchain-Integrated Edge-Cloud-Enabled Healthcare Data Analytics Based on Distributed Federated Learning and Deep Neural Networks," Mesopotamian Journal of CyberSecurity: Vol. 5: Iss. 3, Article 9.
DOI: https://doi.org/10.58496/MJCS/2025/060
Available at: https://map.researchcommons.org/mjcs/vol5/iss3/9