Advancements in Heart Disease Diagnosis: Harnessing Predictive Modeling Techniques for Cardiovascular Health Management

Abstract

This research paper investigates predictive modeling techniques for heart disease diagnosis utilizing comprehensive cardiovascular health data. Leveraging a dataset sourced from the University of California, Irvine Machine Learning Repository, the research focuses on 1,236 patients’ attributes, including age, sex, blood pressure, cholesterol levels, and exercise habits, among others. The analysis employs a combination of data preprocessing, exploratory data analysis, and predictive modeling using both traditional machine learning (ML) and deep learning (DL) approaches. The predictive models aim to classify patients into different degrees of coronary artery disease based on their health attributes. Key methodologies include feature normalization, dropout regularization, and weight regularization to enhance model performance and prevent overfitting. The research compares the effectiveness of categorical and binary classification models, evaluating their accuracy, precision, recall, and F1-score metrics. Results indicate promising performance, with the binary classification model achieving an accuracy of 83.61% on the testing dataset. This research contributes to the ongoing efforts in leveraging advanced computational techniques to aid in the early detection and diagnosis of heart disease, ultimately facilitating better patient care and management strategies.