A novel blockchain-based architectural modal for healthcare data integrity: Covid19 screening laboratory use-case

Area of Science:

• Medical Informatics
• Blockchain Technology
• Artificial Intelligence

Background:

• Ensuring the integrity and security of sensitive healthcare data is critical for AI-driven medical research.
• Interoperability between heterogeneous data sources and existing hospital information systems (HIS) remains a significant challenge.
• Current data protection models require enhancement to address the complexities of data collection, cleansing, and processing in research.

Purpose of the Study:

• To propose a novel blockchain-based architectural model for securing healthcare data in AI medical research.
• To enhance data integrity, interoperability, and privacy protection throughout the research data lifecycle.
• To establish a trusted layer for medical research by integrating with existing healthcare information systems.

Main Methods:

• Implementation of a blockchain-based architecture combining continuous healthcare IoT architecture and Hyperledger Fabric.
• Utilization of HL7 FHIR (Fast Healthcare Interoperability Resources) standardized data structure for interoperability with HIS.
• Development of a four-component trust layer model including FHIR integration, blockchain for access control and auditing, distributed architecture for privacy, and an API.

Main Results:

• The proposed architecture ensures the integrity of healthcare-sensitive data within an AI-based medical research context.
• Interoperability is achieved with existing FHIR-based HIS, enhancing data quality from heterogeneous sources.
• A robust security and data protection model is established, supporting privacy through a distributed network of trusted nodes.

Conclusions:

• The blockchain-based model provides a trustworthy framework for AI medical research by securing sensitive data.
• HL7 FHIR standardization and Hyperledger Fabric integration facilitate seamless data exchange and enhance data management.
• This approach offers a scalable and secure solution for protecting patient data while advancing medical research.