Mobile E-Health On-Demand Knowledge Sharing with Copyright Protection: Joint Blockchain and NFT Approach

• Published in: IEEE International Conference on Communications (2003) pp. 6193 - 6198
• Main Authors: Hao, Guozhi, Wu, Jun, Mumtaz, Shahid
• Format: Conference Proceeding
• Language: English
• Published: IEEE 28.05.2023
• Subjects: Clustering algorithms; Copyright protection; Heuristic algorithms; Knowledge graphs; Medical services; Privacy; Smart contracts
• ISSN: 1938-1883
• DOI: 10.1109/ICC45041.2023.10278976

Nowadays, empowered by mobile networks, electronic health (E-health) can bring more advanced medical services. Electronic health records (EHRs) with rich medical knowledge have gained increasing popularity for supporting E-health. Blockchain-based secure storage and access are novel trends for EHRs, but there are still following unresolved problems in this area. On one hand, specific medical tasks (e.g., COVID-19 diagnosis) require corresponding EHRs, but it lacks the medicine knowledge graph to help doctors or researchers find the EHRs on-demand in the massive distributed and encrypted medical data. On the other hand, as the documents include knowledge, EHRs with digital copyrights shared by medical institutions or patients need to be protected during sharing. To address these challenges, this paper proposes a blockchain and Non-Fungible Token (NFT) empowered on-demand medicine knowledge sharing architecture for EHRs. First, we propose a medicine knowledge graph construction scheme based on smart contracts and medical task knowledge relationships. Second, to provide on-demand EHRs sharing, we design the EHRs matching and clustering algorithms, regarding the dynamic importance and similarity of graph nodes. Third, we establish the interplanetary file address driven NFT minting mechanism for EHRs to protect digital copyrights. Finally, we conduct experiments in Ethereum using real medical datasets, which demonstrates the feasibility and efficiency of the proposed architecture. To our best knowledge, this work is the first to realize the medicine knowledge graph with copyright protection for EHRs.