Revolutionizing healthcare: An IoT-driven approach to remote patient health monitoring and management during the pandemic and beyond

The integration of Internet of Things (IoT) technologies into the healthcare sector has witnessed substantial growth, particularly during global health emergencies such as the COVID-19 pandemic. This research introduces a Smart Health Monitoring System (SHMS) that enables real-time patient health tracking and environmental monitoring using IoT and machine learning (ML). The primary goal of the system is to provide continuous and remote monitoring of vital signs, including Body Temperature (BT), Heart Rate (HR), Environmental Temperature (ET), and Environmental Humidity (EH). Sensor-based data acquisition is managed through microcontroller hardware, with data transmitted via Wi-Fi to cloud-based platforms accessible through smartphones, laptops, and other internet-enabled devices. The system processes data using machine learning models—Logistic Regression and Decision Tree—to predict the patient’s health status with high accuracy. Results indicate that the Logistic Regression model outperforms the Decision Tree model, achieving an accuracy rate of 88.89 %. Additionally, the SHMS architecture is scalable, supporting multi-user environments and large numbers of connected devices, making it suitable for real-world healthcare deployment. To enhance pandemic responsiveness, the system can be extended to measure additional parameters such as Respiratory Rate (RR) and Oxygen Saturation (SpO₂), which are essential during outbreaks of respiratory diseases like COVID-19 and influenza. This solution offers an effective and accessible tool for early detection, timely intervention, and reduced burden on healthcare infrastructure, especially during health crises.