Safeguarding Patient Data-Sharing: Blockchain-Enabled Federated Learning in Medical Diagnostics

Document Type

Article

Publication Title

IEEE Transactions on Sustainable Computing

Abstract

Medical healthcare centers are envisioned as a promising paradigm to handle vast data for various disease diagnoses using artificial intelligence. Traditional Machine Learning algorithms have been used for years, putting the sensitivity of patients' medical data privacy at risk. Collaborative data training, where multiple hospitals (nodes) train and share encrypted federated models, solves the issue of data leakage and unites resources of small and large hospitals from distant areas. This study introduces an innovative framework that leverages blockchain-based Federated Learning to identify 15 distinct lung diseases, ensuring the preservation of privacy and security. The proposed model has been trained on the NIH Chest Ray dataset (112 120 X-Ray images), tested, and evaluated, achieving test accuracy of 92.86%, a latency of 43.518625 ms, and a throughput of 10034017 bytes/s. Furthermore, we expose our framework blockchain to stringent empirical tests against leading cyber threats to evaluate its robustness. With resilience metrics consistently nearing 87% against three evaluated cyberattacks, the proposed framework demonstrates significant robustness and potential for healthcare applications. To the best of our knowledge, this is the first paper on the practical implementation of blockchain-empowered FL with such data and several diseases, including multiple disease coexistence detection.

DOI

10.1109/TSUSC.2024.3409329

Publication Date

1-1-2024

Keywords

Adversarial Attacks, Analytical models, Blockchain, Cybersecurity, Data models, Data privacy, Data sharing, Federated Learning, Federated learning, Lung Disease, Medical services, Multi-Label, Predictive models, Remote Healthcare, Security, X-Ray

This document is currently not available here.

Share

COinS