Coronary Artery Disease Prediction Using Enhanced Multi Layer DCNN

Abstract

Coronary Artery Disease(CAD) is a prevalent and life-threatening cardiovascular condition affecting millions of individuals globally. Early detection and accurate prediction of CAD are vital for timely intervention and prevention of severe cardiac events. Convolutional Neural Networks (CNNs) and other deep learning approaches have recently demonstrated amazing effectiveness in a number of medical applications, including illness prediction. This research proposes an innovative approach, Enhanced Multi-Layer Deep Convolutional Neural Network (EML-DCNN), for the prediction of Coronary Artery Disease. The proposed EML-DCNN architecture integrates advanced deep learning concepts, feature engineering, and data augmentation techniques to enhance the model's predictive performance. The multi-layer structure of EML-DCNN enables the automatic extraction of intricate patterns and features from medical imaging data, specifically focusing on coronary artery images. Additionally, the model incorporates attention mechanisms and residual connections, enhancing its ability to capture subtle details and relationships within the data. To validate the efficacy of the proposed EML-DCNN model, extensive experiments were conducted on a large and diverse dataset comprising coronary artery images obtained from various medical sources. The results demonstrate superior predictive accuracy, sensitivity, and specificity compared to existing CAD prediction models. Moreover, the model's interpretability is enhanced through visualization techniques, providing valuable insights into the features influencing the prediction process.