ENHANCED PREDICTION OF CORONARY ARTERY DISEASE USING LOGISTIC REGRESSION

Abstract

Coronary Artery Disease (CAD) remains a leading cause of global morbidity and mortality, emphasizing the urgent need for accurate and interpretable prediction models to facilitate timely interventions and improve patient outcomes. This study investigates the application of Logistic Regression for CAD prediction, leveraging a dataset of 303 patients and 13 clinical features obtained from the UCI Machine Learning Repository. Recognizing the limitations of traditional risk assessment methods, this research explores the potential of Logistic Regression to enhance CAD prediction accuracy through a streamlined and easily implementable approach. The dataset, which encompasses demographic factors, clinical measurements, and lifestyle indicators, was subjected to rigorous analysis to evaluate the model's performance. A Logistic Regression model was developed using Python's scikit-learn library and assessed using a comprehensive set of evaluation metrics, including accuracy, precision, recall, F1-score, and the Area Under the Receiver Operating Characteristic curve (AUC-ROC). On a test set of 61 instances, the model achieved an overall accuracy of 82%, demonstrating its ability to correctly classify individuals with and without CAD. The precision and recall scores for Class 0 (absence of CAD) were 79% and 82%, respectively, while for Class 1 (presence of CAD), the precision and recall scores were 84% and 82%, respectively, indicating balanced performance across both classes. The model exhibited an AUC-ROC of 0.89, signifying strong discriminatory ability. These findings suggest that Logistic Regression can serve as a valuable tool for CAD risk assessment, providing a foundation for more advanced predictive models and contributing to improved cardiovascular health management...