Cardiac Status Prediction using Machine Learning

Abstract

This work focuses on creating an IoT platform using machine learning to predict cardiac status with a Raspberry Pi. The system uses a DS18B20 sensor for temperature measurements and a MAX30100 sensor for monitoring heart rate and oxygen saturation. It incorporates various user-specific health features such as age, gender, smoking status, cigarettes per day, hypertension prevalence, blood pressure medication usage, diabetes status, BMI, heart rate, and temperature to improve prediction accuracy. The data collected is processed on the Raspberry Pi using a pre-trained machine learning model (Logistic Regression) to predict cardiac health status. A Flask-based web application provides an intuitive user interface, allowing users to input their health data and receive cardiac status predictions. This work aims to offer a low-cost, efficient, and user-friendly tool for early detection and monitoring of cardiac health, with potential benefits in preventive healthcare and personalized medicine