Publication

Abstract : Heart failure is a major factor in morbidity and death. Worldwide. Early detection of heart failure is critical to improving patient outcomes. Machine learning techniques have been used for heart failure detection in the past few years. This study suggests a novel approach for heart failure detection using a Radial Basis Function (RBF) neural network with Genetic Algorithm (GA) optimization. The suggested approach is applied to the publicly available heart failure dataset, and its performance is evaluated using various performance metrics. The proposed method uses data from 12 different features to train the RBF network and GA to find the optimal network parameters. The efficacy of the suggested method was assessed using a dataset of heart failure patients and healthy individuals. According to the results, the accuracy of the proposed method was achieved, which is 92.6%. These results outperformed several existing methods, demonstrating the potential of the proposed approach for heart failure detection. The proposed method can provide a reliable, non-invasive, and cost-effective tool for the early detection of heart failure, which can help reduce the burden of this disease on individuals and healthcare systems.