CARDIO ALERT: Proactive Heart Attack Monitoring using Sensors and AI Algorithms

This study introduces an efficient heart attack detection system that combines ECG monitoring and pulse rate sensors to enhance diagnostic accuracy. Leveraging data from both sources, the system applies machine learning algorithms—including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and Random Forest (RF)—to classify ECG patterns into normal and myocardial infarction categories. Additionally, an ensemble model integrating these algorithms was developed to further improve prediction performance. The ensemble approach captures complementary strengths from each classifier, resulting in robust and reliable classification outcomes in both training and testing stages. Future implementation of this model on a wearable device aligned with the Internet of Medical Things (IoMT) could enable real-time, continuous health monitoring, providing early alerts for heart attack symptoms and enhancing patient outcomes through proactive care and reduced need for hospital visits. This work demonstrates the potential of machine learning and IoMT-enabled wearables to advance cardiovascular monitoring and support critical, timely interventions.