DT-DOFL: Digital-Twin-Empowered Decentralized Online Federated Learning for User-Centered Smart Healthcare Service Systems

This article explores the user-centered theory in computational smart healthcare service systems (SHSS) and proposes a comprehensive SHSS solution based on digital twin (DT) and decentralized federated learning (DFL). To clarify the interaction between users, products, and services in SHSS, a hybrid framework called user-centered data-driven product and smart healthcare service system (UDP-SHSS) is proposed. The key challenges related to medical data privacy protection, real-time user state monitoring and data updates, and the integration of resources across decentralized medical institutions are identified through the analysis of this framework. To address these challenges, the DT-empowered DFL Framework is designed, where DT maps physical hospital entities to the virtual decentralized network and DFL offers a decentralized model interaction scheme to the decentralized network. To construct the dynamic real-time and privacy-preserving objectives of UDP-SHSS, the DT-based decentralized online federated learning (DT-DOFL) algorithm is developed, which models the framework with graph theory to account for the real-world communication scenarios between clients and incorporates differential privacy (DP) mechanisms to ensure user privacy. Given the black-box nature of DFL models, the one-point bandit feedback (OPBF) mechanism is employed to address the online convex optimization problem in UDP-SHSS. Rigorous proofs demonstrating that the algorithm achieves ϵ-DP and sublinear convergence are given. Finally, several experiments on various diseases in SHSS are conducted to verify the effectiveness of our framework and algorithm.