Abstract Nowadays, artificial intelligence (AI), machine learning (ML), and deep learning (DL) algorithms have emerged as promising avenues for designing robust, scalable diagnostic and prognostic models from medical data. Despite the high performance these models exhibit, they still face significant challenges in the healthcare domain when trained with the traditional centralized learning paradigm, including data security, data heterogeneity, data scarcity, and computational limitations. Recent developments in decentralized learning have attracted attention from both academia and industry, providing a promising way to train high-performance AI models while maintaining data privacy. For instance, recent developments in federated learning have enabled the aggregation of local model weights to obtain a global model, rather than collecting data from each client for global training. Other emerging techniques have made use of blockchain techniques to ensure a safe peer-to-peer transaction, providing more options and possibilities for decentralized learning. In this review, we aim to explore the present and future of decentralized technologies in healthcare domain, where data privacy and model performance are high priorities in data sharing. This study primarily focuses on reviewing different decentralized learning paradigms combined with AI technologies in healthcare applications, including their difference in methodologies, performance, challenges, and future directions. We also highlighted the influence of base model selections on decentralized systems, such as performance variety, computational cost, and communication burden. In this context, we demonstrate that decentralized learning methods have a good potential to improve hospital collaboration, while making a trade-off between system performance and data privacy at a low cost. Furthermore, we provide future directions for current decentralized methods by summarizing the state of the art works and identifying open problems.
Zhao et al. (Sun,) studied this question.