Privacy-Preserving Healthcare Fraud Detection: A Survey of Trust-Centric Federated Learning, Blockchain, and Explainable AI
Abstract
The privacy of sensitive medical information is essential since the application of effective analytics is crucial to identifying healthcare fraud. Regulatory and security limitations do not always allow the use of the traditional centralized approaches. This survey presents the current trend in privacy-conscious fraud detection, and it pays a lot of attention to the application of trust-centric federated learning along with blockchain and explainable artificial intelligence. It talks about the potential of the decentralized learning systems to train models without sharing raw data, and blockchain can be employed to ensure transparency and auditability. Also, the issue of explainable models in increasing interpretability and regulatory compliance is addressed. The essential issues are examined, i.e., adversarial robustness, communication overhead, and system scalability. The questionnaire concludes with the future research directions of developing safe, trusted, and effective healthcare fraud detection systems.