A Novel Mistfog Federated Learning Model for Heart Disease Detection in Smart Healthcare

Healthcare has been regarded as the pivotal pillar for human prosperity and economic growth which has shifted the focus onto smarter healthcare in smart cities. Despite several efforts, heart diseases pose a dangerous risk to individual life and are the cause of higher mortality rates due to sudden strokes and hence need to be detected in real-time. Researchers have put several efforts to address the overall prediction accuracy rate. However, this has led to the use of innovative and integrated paradigms vis-à-vis cloud computing (CC), fog computing (FC), and mist computing (MC) which have skewed computing and latency requirements and the use of software defined networks (SDN), coupled with federated learning model utilizing ensemble learning to synergize the overall performance through improvements in prediction accuracy and execution time from the data captured from Internet-of-Things (IoT) devices. This chapter proposes a novel use-case of MistFog which utilizes an integrated approach of multiple computing paradigms, and state-of-the-art networks and learning models for heart disease detection and prediction. Finally, the proposed MistFog is also compared with other work through the proof of concept to show its efficacy in terms of network communication. © 2025 selection and editorial matter, Diptendu Sinha Roy, Mir Wajahat Hussain, K. Hemant Kumar Reddy, Deepak Gupta; individual chapters, the contributors.