AN INTELLIGENT CLINICAL DECISION SUPPORT SYSTEM FOR HEART DISEASE PREDICTION USING CNN

Abstract

Cardiovascular diseases remain one of the most critical health problems worldwide, leading to millions of deaths every year. Early prediction and diagnosis of heart disease are essential for effective treatment and prevention. This project proposes an Intelligent Clinical Decision Support System (CDSS) that utilizes Convolutional Neural Networks (CNN) to predict the risk of heart disease using clinical and medical data. The system integrates machine learning and deep learning techniques to assist healthcare professionals in making accurate and timely medical decisions. Traditional heart disease prediction approaches mainly rely on statistical analysis or classical machine learning algorithms such as Logistic Regression, Decision Trees, Random Forest, and Support Vector Machines. Although these techniques provide reasonable prediction accuracy, they often require manual feature extraction and may fail to capture complex nonlinear relationships in medical data. To overcome these limitations, the proposed system applies CNN-based deep learning models capable of automatically learning important features from patient datasets. The CNN model analyzes patient attributes such as age, blood pressure, cholesterol level, ECG results, and other medical parameters to determine the likelihood of heart disease. By integrating intelligent learning capabilities with a clinical decision support framework, the system improves prediction accuracy and supports doctors in diagnosing cardiovascular conditions more efficiently.