Health Monitoring System Integrating IoT and Machine Learning for Cardiac Prognosis

DOI: https://doie.org/10.10399/JBSE.2025314930

Bhakti Y Sathe, Maheshwari Biradar, Swapnil Waghmare, Jagadish S Jakati

Keywords:

IoT, sensors, machine learning, Random forest

Abstract:

The integration of IoT (Internet of Things) in healthcare is transforming diagnosis and management of heart disease through continuous, real-time monitoring. This study explores a system that utilizes wearable devices such as ECG sensor, pulse oxymeter to collect key health data including heart rate, ECG, blood pressure, and oxygen saturation. The collected data is wirelessly transmitted to cloud platforms for analysis using machine learning algorithms, enabling early detection of heart disease. The system provides healthcare professionals with the ability to remotely monitor patients, facilitating timely interventions and reducing the need for frequent hospital visits. Machine learning models such as Random Forest, Support Vector Machines (SVM), and deep learning techniques like CNN (Convolutional Neural Network) are employed to detect patterns, predict potential heart disease events, and classify different heart rhythms. These systems offer numerous benefits, including the reduction of healthcare costs, early detection of abnormalities, and proactive interventions. The results indicate that IoT-based systems significantly improve patient outcomes by enabling continuous health monitoring and facilitating personalized healthcare.

PDF