Recent Advances in Smart Healthcare Patient Monitoring System for IoT-Based Healthcare System Using Enhanced Residual Multi-Scale Diverged Self-Attention Network: A Systematic Review

Abstract

The rapid advancement of Internet of Things (IoT) technologies has significantly transformed modern healthcare systems by enabling real-time patient monitoring, remote diagnosis, and predictive analytics. Smart healthcare systems leverage IoT devices such as wearable sensors, wireless body area networks (WBAN), and cloud platforms to continuously collect physiological data including heart rate, blood pressure, oxygen saturation, and body temperature. These systems, when integrated with deep learning (DL) models, enhance diagnostic accuracy and enable early detection of diseases. Recent research has focused on advanced deep learning architectures such as convolutional neural networks (CNN), recurrent neural networks (RNN), and attention-based models for analyzing complex healthcare data. In particular, self-attention mechanisms and multi-scale feature extraction techniques have shown significant improvements in capturing long-range dependencies and multimodal correlations in patient data. Studies indicate that integrating IoT with deep learning enables efficient real-time monitoring and improves clinical decision-making. This review presents a comprehensive analysis of recent advancements in IoT-based smart healthcare monitoring systems, with a focus on enhanced residual multi-scale diverged self-attention networks. The paper evaluates different methodologies based on accuracy, scalability, latency, and computational efficiency. Furthermore, it highlights challenges such as data privacy, energy consumption, and interoperability. Finally, future research directions including federated learning, edge intelligence, and attention-based architectures are discussed.