Towards Collaborative Machine Learning Driven Healthcare Internet of Things

Abstract

The relationship between technology and healthcare due to the rise of Intelligent Internet of Things (IoT) and the rapid public embracement of medical-grade wearables has been dramatically transformed in the past few years. Powered by IoT, technology brought disruptive changes and unique opportunities to the healthcare industry including personalized services, tailored content, improved availability and accessibility, and cost-effective delivery. Despite these exciting advancements in transition from clinic-centric to patient-centric healthcare, many challenges still need to be tackled. The key to successfully unlock and enable this digital shift is adopting a holistic architecture to provide high-level of quality in attributes such as latency, availability, and real-time analytics processing. In this paper, we discuss applicability of Intelligent IoT based on Collaborative Machine Learning in healthcare and medicine by presenting a holistic multi-layer architecture. This solution enables real-time actionable insights which ultimately improves decision-making powers of patients and healthcare providers. The feasibility of such architecture is investigated by a case study, ECG-based arrhythmia detection, based on deep learning and Convolutional Neural Network (CNN) methods distributed across endpoint IoT Devices, Edge (Fog) nodes, and Cloud servers.