Machine Learning Driven Remote Monitoring for Predictive Management of Chronic Heart Disease

Managing chronic heart disease (CHD) is critical for improving patient outcomes and easing the burden on healthcare systems. With wearable devices and health monitoring tools, machine learning can help in early detection and prevention of heart-related events. This paper explores the use of Transformer Networks, Support Vector Machines (SVM), and Light Gradient Boosting Machine (LightGBM) to predict heart disease outcomes using the "Heart Disease" dataset from Kaggle. Transformer Networks analyze sequential health data, SVM identifies non-linear relationships, and LightGBM predicts outcomes based on clinical and demographic factors. Each model's performance is evaluated using accuracy, precision, recall, and F1-score. The study highlights how these approaches can improve early detection and treatment, with potential integration into remote monitoring systems to reduce hospital admissions and provide timely care for CHD patients.