Secure healthcare data management using federated learning, blockchain, and explainable artificial intelligence: a systematic review
Abstract
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…
How strong is the evidence?
Evidence Hub reads this as a systematic review, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid.
Read the paper
Related studies
- Active Learning during Federated Learning for Object Detection
- Fairness-aware federated learning
- Decentralized Federated Learning
- Building a Personally Identifiable Information Recognizer in a Privacy Preserved Manner Using Automated Annotation and Federated Learning
- Preservation of Patient Level Privacy: Federated Classification and Calibration Models
- Efficient explainable federated learning
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.