Health Monitoring System for Heart Attack Risk Prediction using IoT and Machine Learning

The initiative centers on the creation of a health monitoring system utilizing Internet of Things (IoT) technology, designed to forecast the likelihood of a heart attack by assessing critical physiological indicators, including Blood Oxygen Saturation (SpO2), Heart Rate (BPM), and Body Temperature. These metrics are collected through a NodeMCU ESP32 microcontroller, which is equipped with a MAX30102 Pulse Oximeter and Heart Rate Sensor, as well as an MLX90614 Infrared Temperature Sensor. The gathered data is subsequently transmitted to a Firebase Realtime Database for processing, utilizing the Arduino IDE. On the client side, an Android application accesses the data from Firebase and employs a Decision Tree Machine Learning Algorithm to evaluate the heart attack risk. The system classifies the risk into three categories based on the input parameters: No Risk, Medium Risk, or High Risk. The objective of this project is to facilitate real-time monitoring and provide early alerts to individuals at risk of cardiovascular complications, thereby allowing for prompt medical response.