Integrated Approaches in Data Mining for Heart Disease Prediction System

Abstract

The healthcare industry accumulates vast amounts of data that remain underutilized for informed decision-making. This research explores advanced data mining techniques to address this issue and presents three distinct prototypes of Heart Disease Prediction Systems (HDPS) employing Decision Trees, Logistic Regression, and Linear Regression. The prototype (IHDPS) demonstrates the unique strengths of each technique, offering a web-based platform capable of answering complex "what if" queries. By analyzing medical profiles such as age, gender, blood pressure and blood sugar, it predicts the likelihood of heart disease and generates important information about patterns and relationships between related medical factors. The second prototype emphasizes the successful application of data mining in healthcare, particularly in heart disease prediction. Collectively, these integrated approaches showcase the potential of data mining in developing scalable, user-friendly, and reliable systems for predicting heart disease, addressing the information-rich yet knowledge-poor landscape of the healthcare industry.