An optimal heart disease prediction using chaos game optimization-based recurrent neural model

Heart disease is the significant reason of increasing death in worldwide. The early prediction of heart disease is obtained as a challenging role and this prevents severe heart diseases like heart attacks, coronary artery disease, etc. So various traditional methods are utilized for early prediction of heart disease but they are expensive and time consuming. Thus a novel Chaos Game Optimization based Recurrent Neural Network (CGO-RNN) is utilized to overcome the issues and improve early prediction of heart disease accurately. The Kernel Principal Component Analysis (KPCA) approach is used to diminish the computational load and dimensionality reduction of the proposed method as well as the features are extracted to categorize the heart samples for accurate and early prediction. The experimentation results revealed an improved performance by satisfying the results of 98.99%, 98.97%, 98.95%, 98.56%, and 98.54%. This determines that the proposed method enhanced the efficiency and makes a reliable prediction of heart disease. © The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of Computer Applications and Management 2023.