Secure healthcare data management using federated learning, blockchain, and explainable artificial intelligence: a systematic review

Due to the rapid digitization of healthcare systems, there has been a huge collection of sensitive personal data of patients. Thus, secure, privacy-preserving, and efficient data management systems are required. Current distributed healthcare systems increasingly use centralized data processing frameworks that are prone to privacy violations, data fragmentation, and malicious attacks. Despite advances in federated learning, blockchain, explainable AI, and incremental optimization, current survey literature studies each technology separately without considering how the four technologies can be harnessed to create synergies. A systematic review of 26 peer-reviewed studies published from 2018 to 2026 indicates that an integrated architecture incorporating federated learning, blockchain, explainable AI, and incremental optimization can be designed. This review identifies ten critical issues that need to be addressed when researching the four technologies. These issues include communication costs, scalability issues, interoperability concerns, limited clinical explainability, and high computational costs when applied in real-time situations. In comparison to privacy, scalability, interpretability, and efficiency, a hybrid approach can help improve data security, boost the interpretability of the models, facilitate data sharing, and prevent data-sharing risks. Overall quality assessment based on the CASP qualitative checklist analysis of all 26 studies indicated an average score of 7.0 out of 10, implying that the quality of the methods used in the studies was acceptable.