AI-Enhanced Blockchain Analytics for Genomic Data Access Control: Toward Explainable and Privacy-Preserving Biomedical Decision Support
Main article
Abstract
Genomic data governance requires systems that are secure, patient-centered, explainable, and operationally usable by biomedical institutions. Conventional role-based access control and centralized audit logging offer baseline protection but often fail to deliver dynamic consent enforcement, cross-institutional traceability, and interpretable risk explanations for complex genomic data requests. This paper develops an AI-enhanced blockchain analytics framework for genomic data access control. The framework combines permissioned blockchain governance, smart-contract consent logic, off-chain encrypted genomic repositories, zero-knowledge verification, and explainable machine-learning models that score access requests before data release. A scenario-based prototype experiment is designed around 48,000 simulated genomic access events representing hospitals, research laboratories, biobanks, and external collaborators. The proposed hybrid model achieves an F1-score of 0.94 and AUROC of 0.97 for high-risk access detection, outperforming rule-only and non-explainable baselines. Explainability analysis shows that consent-scope mismatch, sensitive variant class, requester-role distance, and unusual request timing are the dominant risk factors. The study contributes a healthcare engineering architecture in which blockchain preserves provenance and accountability, AI improves adaptive risk identification, and explanation interfaces support biomedical decision making without exposing raw genomic records.
