Published Paper Details:

Heart disease (HD) is a serious health problem that has affected many people all over the world. Shortness of breath, muscular weakness, and swollen feet are prominent signs of HD. Due to some factors, including accuracy and execution time, present heart disease diagnosis techniques are not very effective in early-time identification. Researchers are working to develop an effective method for the detection of heart disease. In this study, we suggested a supervised machine learning-based system that can quickly and accurately diagnose cardiac problems. The categorization techniques used in the system's development, including support vector machines, decision trees, and random forests, are all included. To increase accuracy, we combined all of the above-mentioned algorithms to create a hybrid algorithm. The classifier's performances are evaluated using the performance measurement metrics. On the features chosen via features selection algorithms, the classifier performances have been evaluated. We produce an enhanced performance level with an accuracy of 95.08% through the prediction model for heart disease with Hybrid Decision Tree, Random Forest, and SVM model. The flask framework website provides the final output. The suggested system can also recommend a food diet to patients who test positive.