Abstract
Continuous monitoring of patient health is essential for early diagnosis and prevention of life-threatening conditions. This project proposes an IoT-based medical patient monitoring system using an ESP32 microcontroller integrated with a temperature sensor, ECG sensor, and SpO₂ sensor to monitor vital physiological parameters in real time. The collected sensor data is processed by the ESP32 and transmitted via Wi-Fi to a web application dashboard, enabling remote access, live visualization, and historical data analysis.
To enhance intelligent health assessment, a machine learning approach using the Random Forest algorithm is implemented. The Random Forest model is trained on historical patient health data to classify patient conditions as normal or abnormal based on temperature, heart rate, ECG features, and oxygen saturation levels. This algorithm is chosen due to its high accuracy, robustness to noise, and ability to handle nonlinear medical data effectively. The trained model is deployed on the server side and continuously analyzes incoming sensor data to predict potential health risks.
When abnormal conditions such as elevated body temperature, irregular ECG patterns, or reduced SpO₂ levels are detected, the system automatically generates alerts on the web dashboard for timely medical intervention. The proposed system provides a cost-effective, scalable, and reliable solution for real-time patient monitoring and predictive healthcare, making it suitable for hospital environments, home care, and telemedicine applications.
Introduction
Healthcare systems require continuous and accurate monitoring of patients to detect critical health conditions at an early stage. Traditional patient monitoring methods depend heavily on manual observation and periodic checkups, which may not provide real-time health information and can lead to delayed medical response. With the advancement of Internet of Things (IoT) technology, remote patient monitoring has become more efficient, reliable, and accessible.
This project presents an IoT-based medical patient monitoring system using an ESP32 microcontroller to monitor essential physiological parameters such as body temperature, ECG signals, and SpO₂ levels. The ESP32 collects data from the sensors and transmits it wirelessly to a web-based dashboard, where patient health data is displayed in real time. Doctors and caregivers can access this dashboard remotely to observe live readings and analyze historical health trends.
To enhance intelligent health analysis, machine learning using the Random Forest algorithm is implemented. The Random Forest model processes the collected sensor data and classifies the patient’s health condition as normal or abnormal with high accuracy. This helps in early detection of health issues such as fever, irregular heart activity, and low oxygen saturation. When abnormal conditions are detected, alerts are generated on the web dashboard for timely medical intervention.
The proposed system provides a cost-effective, scalable, and smart healthcare monitoring solution suitable for hospitals, home care, and remote medical applications, improving overall patient safety and healthcare efficiency.


Objectives
• To monitor patient health using an ESP32 microcontroller.
• To measure body temperature, ECG, and SpO₂ using medical sensors.
• To display patient data on a web-based dashboard in real time.
• To use the Random Forest algorithm to detect abnormal health conditions.
• To generate alerts when abnormal readings are detected.
• To provide a low-cost and reliable patient monitoring system.