IoT-enabled smart healthcare system with machine learning for real-time vital sign monitoring and anomaly detection

This paper presents an innovative IoT-enabled smart healthcare system that combines real-time vital sign monitoring with machine learning-based anomaly detection. The system utilizes a MAX30102 photoplethysmography sensor interfaced with an ESP-32 microcontroller to collect heart rate and blood oxygen saturation (SpO2) data. MQTT protocol ensures efficient data transmission to a cloud database. A long short-term memory (LSTM) neural network architecture is employed for time-series prediction of vital signs and anomaly detection. The system demonstrates high accuracy, with mean squared errors of 0.3% in offline testing and over 90% accuracy in real-time prediction. This affordable and scalable solution offers continuous monitoring capabilities, making it viable for widespread adoption in healthcare settings. The integration of IoT and machine learning techniques provides a robust framework for early detection of health anomalies, potentially improving patient care and outcomes in various medical scenarios.