Predictive Model for M-Health (Cardiovascular Diseases) using ML Application

This study uses a dataset of 70000 participants to predict the presence or absence of cardiovascular disease using 11 predictor characteristics. These variables comprise the primary CVD risk factors, such as a patient’s blood pressure and whether or not they smoke or engage in physical activity. Each observation in this collection represents a representation of a specific patient. Emerging mobile health (M-Health) systems are an example of cutting-edge technologies that use big data, artificial intelligence, deep learning, and other machine learning approaches. To predict CVD categorization, the supervised machine learning techniques XGBoost, Random Forest, and Logistic Regression are applied. In order to make inferences about likely optimizations, the original dataset is additionally sorted into groups using an unsupervised model known as the K-means clustering technique.