A Proficient Framework for Coronary Artery Disease Prediction using Logistic Regression

The healthcare industry is actively researching heart disease prediction to identify people who have a higher likelihood of developing this condition. Due to the increasing prevalence of heart disease, it is vital to accurately identify and treat people at risk for it. Machine learning-based techniques offer potential benefits in the early detection and prevention of heart disease, but developing such methods is a complex task. Many countries lack the necessary cardiovascular expertise, and there is a significant number of misdiagnosed cases. Accurate and efficient prediction of heart disease at an early stage is essential for managing and treating the condition effectively, and digital patient records can support clinical decision-making. The ultimate goal is to reduce the incidence and mortality rates associated with heart disease. In this research, several supervised machine-learning algorithms have been developed and compared for their effectiveness in predicting heart disease, including Logistic Regression, Decision Tree, Naïve Bayes, KNN, and Xtreme Gradient Boosting (XGB). Among these models, Logistic Regression has demonstrated an accuracy of 0.86 and precision of 0.90, making it a promising approach for heart disease prediction.