Main article

Amirul Hakim Roslan
Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pekan 26600, Pahang, Malaysia
Nur Aina Zulkifli
Faculty of Information and Communication Technology, Universiti Teknikal Malaysia Melaka, Durian Tunggal 76100, Melaka, Malaysia
Faridah Mohd Noor
Faculty of Bioengineering and Technology, Universiti Malaysia Kelantan, Jeli 17600, Kelantan, Malaysia
Kelvin Tan Wei Ming
Faculty of Computer Science and Information Technology, Universiti Tun Hussein Onn Malaysia, Parit Raja 86400, Johor, Malaysia
Siti Hajar Abdullah*
College of Computing, Informatics and Mathematics, Universiti Teknologi MARA, Shah Alam 40450, Selangor, Malaysia
sitihajar.abdullah@uitm.edu.my

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.

Article details

How to Cite

Roslan, A. H., Zulkifli, N. A., Mohd Noor, F., Wei Ming, K. T., & Abdullah, S. H. (2024). AI-Enhanced Blockchain Analytics for Genomic Data Access Control: Toward Explainable and Privacy-Preserving Biomedical Decision Support. Journal of AI Analytics and Applications, 2(3), 27-43. https://doi.org/10.63646/jaiaa.2024.020302