Traceability in Federated Learning in Healthcare
Abstract
Federated learning (FL) enables privacy-preserving analytics on distributed healthcare data, but achieving transparency remains a critical challenge for trust and accountability. This scoping review focuses on traceability as a core component of transparency and systematically assesses traceability in FL within healthcare. Following the PRISMA-ScR methodology, we screened 125 articles across four databases, of which 53 met our inclusion criteria. Preliminary results show that 77.36% of articles rely on blockchain to support traceability, while only a small subset addresses healthcare applications, and comprehensive evaluation frameworks regarding traceability are largely lacking. Future research should explore the integration of blockchain in federated learning platforms in healthcare for traceability to enhance trust, auditability and accountability in clinical practice.
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.