An intelligent blockchain strategy for decentralised healthcare framework.

Area of Science:

• Blockchain Technology
• Cybersecurity
• Medical Data Management

Background:

• Secure medical data sharing is a major blockchain challenge.
• Existing methods suffer from high time/memory use and low confidentiality.
• Data integrity is compromised by security threats and large unstructured records.

Purpose of the Study:

• To present a novel hybrid Deep Belief-based Diffie Hellman (DBDH) security framework.
• To protect medical data from malicious events and ensure data integrity.
• To improve the efficiency and confidentiality of secure medical data transfer.

Main Methods:

• Utilized a deep belief neural system for continuous system monitoring and attack identification.
• Implemented a hybrid DBDH framework incorporating deep belief networks and Diffie Hellman.
• Employed homomorphic properties for hash calculation on encrypted data and a verification module for hash comparison.

Main Results:

• The DBDH framework demonstrated enhanced security and confidentiality for medical data.
• The model showed reduced time consumption and memory usage compared to existing approaches.
• Cryptanalysis confirmed the model's robustness against malicious attacks.

Conclusions:

• The proposed DBDH framework effectively secures medical data on blockchain.
• This novel approach addresses the limitations of existing blockchain security methods.
• The framework offers a promising solution for secure and efficient medical data sharing.