Identification of Heart Diseases using Novel Machine Learning Method
Rayavarapu Veeranjaneyulu, Sampath Boopathi, Jonnadula Narasimharao, Keerat Kumar Gupta, R. Vijaya Kumar Reddy, R. Ambika
Abstract
This study aims to enhance feature variety and organizationprocesses for heart disease prediction using three different approaches. The integration of machine learning perception and enhanced motion based on the dragonfly algorithm (MLP-EBMDA) has been the primary focus of the research. The suggested system has been assessed through number of factors, recall, accuracy rate, F1-score, and precision. After execution of the algorithm, the precision, f1-score, recall, accuracy, and sensitivity of the proposed MLP-EBMDA are each 87%. The accuracy of the MLP-EBMDA-based informative entropy-based random forest approach is 84 percent in predicting heart disease. This distinction can be made between patients with cardiac disease and healthy patients.