Published Paper Details:

Heart disease is a major global health concern, accounting for a significant number of deaths annually. Early detection and accurate prediction of heart disease are crucial for effective management and treatment. Machine learning techniques, particularly classification methods, have shown promise in analyzing clinical data for heart disease detection. However, existing approaches have limitations in terms of data preprocessing, feature selection, and model optimization. In this paper, we propose a novel approach that combines hybrid brave-hunting optimization with a support vector machine (SVM)-coupled deep convolutional neural network (CNN) model for heart disease prediction. The hybrid optimization method enhances feature selection and model performance, while the deep CNN model leverages the power of neural networks for capturing complex relationships in the data. Our experimental results demonstrate the effectiveness of the proposed approach in accurately predicting heart disease. This research contributes to the development of a cost-effective and efficient decision support system for heart disease detection, potentially aiding in early intervention and improved patient outcomes.