Published Paper Details:

Heart disease remains one of the leading causes of mortality worldwide, necessitating the development of accurate and efficient prediction systems to enable timely diagnosis. This study evaluates the performance of four machine learning models--Logistic Regression, Decision Tree, Support Vector Machine (SVM), and Convolutional Neural Network (CNN)--for heart disease detection. The models were trained and tested on a structured dataset, and their performance was compared using metrics such as accuracy, precision, recall, and F1-score. CNN demonstrated the highest performance with an accuracy of 89%, outperforming traditional models due to its ability to capture complex data patterns. Logistic Regression and SVM achieved comparable results with an accuracy of 88%, highlighting their effectiveness in structured data environments. The Decision Tree model showed relatively lower performance with an accuracy of 85%, limited by its overfitting tendencies. This comparative study highlights the strengths and limitations of each model, providing valuable insights into their suitability for heart disease prediction. The findings emphasize the potential of CNN in delivering reliable predictions and pave the way for future enhancements through model optimization, ensemble techniques, and real-world deployment in medical applications