Blockchain for Securing AI-Driven Healthcare Systems: A Systematic Review and Future Research Perspectives

Abstract

The integration of AI in healthcare has significantly advanced diagnostics, patient monitoring, and personalized treatments. However, the reliance on vast datasets raises critical concerns about data privacy, security, and trustworthiness. Blockchain technology, with its decentralized and immutable nature, has emerged as a promising solution to these challenges. This systematic review aims to explore the role of blockchain in securing AI-driven healthcare systems, evaluating its potential to enhance data security, privacy, and interoperability while identifying key challenges and future research directions. The review followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, conducting a comprehensive search across databases such as IEEE (Institute of Electrical and Electronics Engineers) Xplore Digital Library, Scopus, Web of Science, and PubMed. Inclusion criteria focused on peer-reviewed studies discussing blockchain and AI integration in healthcare, while exclusion criteria eliminated irrelevant or non-empirical studies. Data extraction captured study characteristics, AI algorithms, blockchain types, key findings, and limitations. Quality assessment was performed using the Joanna Briggs Institute (JBI) Critical Appraisal Checklist, evaluating methodological rigor, innovation, and reproducibility. The review included 15 studies highlighting blockchain's role in securing AI-driven healthcare systems. Key findings demonstrated blockchain's effectiveness in enabling decentralized data sharing (e.g., federated learning (FL)), enhancing data integrity, and improving diagnostic accuracy. However, challenges such as scalability, interoperability, and regulatory compliance were recurrent. The quality assessment revealed moderate-to-high methodological quality but underscored gaps in reproducibility and real-world validation. Blockchain technology holds transformative potential for securing AI-driven healthcare systems by addressing critical privacy and security concerns. However, the field remains nascent, with significant hurdles in scalability, technical standardization, and ethical governance. Future research should prioritize hybrid blockchain architectures, clinical trials, and interdisciplinary collaboration to bridge these gaps and realize the full potential of blockchain-AI integration in healthcare.

Ähnliche Arbeiten