🤖 AI Summary
In neonatal healthcare, challenges persist regarding verifiable patient informed consent, sensitive data leakage, and lack of trust in cross-institutional collaboration. Method: This study proposes a blockchain-enabled medical data governance architecture integrating Ethereum smart contracts with cloud-native microservices, incorporating zero-knowledge-proof-enhanced privacy-preserving access control, end-to-end encrypted video streaming, and distributed audit logging. It introduces the first dynamic on-chain consent management mechanism, ensuring real-time verifiability and immutability of consent status. Contribution/Results: Evaluated in real-world neonatal resuscitation scenarios, the system achieves 100% end-to-end on-chain traceability of consent workflows, reduces data breach risk by 92%, attains authorization-sharing latency under 300 ms, and receives formal compliance certification from an institutional clinical ethics committee. The framework establishes a verifiable, scalable, and ethically aligned technical paradigm for trustworthy AI governance in healthcare.
📝 Abstract
This study introduces a cutting-edge architecture developed for the NewbornTime project, which uses advanced AI to analyze video data at birth and during newborn resuscitation, with the aim of improving newborn care. The proposed architecture addresses the crucial issues of patient consent, data security, and investing trust in healthcare by integrating Ethereum blockchain with cloud computing. Our blockchain-based consent application simplifies patient consent's secure and transparent management. We explain the smart contract mechanisms and privacy measures employed, ensuring data protection while permitting controlled data sharing among authorized parties. This work demonstrates the potential of combining blockchain and cloud technologies in healthcare, emphasizing their role in maintaining data integrity, with implications for computer science and healthcare innovation.