Empowering Healthcare: Edge Computing and ML for Early Heart Attack Detection And Prevention

Heart diseases are a major cause of death among humans, and early detection of such conditions plays a crucial role in saving many lives. Due to technological advances, especially in the field of health care, we have created a health care system aimed at detecting heart diseases, including heart attacks, especially in remote areas. Our approach involves working within an edge computing environment to mitigate network issues and ensure real-time performance. This is achieved by integrating Internet of Things (IoT) devices and a local server to store and archive information locally, while also establishing a connection with the cloud to process broad sets of data. It ensures that the computational and processing capabilities of devices at the edge are used to carry out training and prediction operations instead of relying on the remote cloud. This allows for improved application responsiveness, privacy preservation, and reduced reliance on an Internet connection. Our study focuses on three different machine learning algorithms (K-Nearest Neighbor (KNN), Random Forest algorithm, and Support Vector Machine (SVM)) and compares their results with the output of the model used. The results showed the superiority of the Random Forest algorithm through model accuracy and… faster training performance and prediction time of less than 42 seconds, with the highest correct prediction percentage reaching 90 percent. Our work focuses on evaluating the effectiveness of the proposed models as well as evaluating their processing time.