Machine intelligence based early prediction methods for Cardiovascular Diseases (CVDs)

Abstract

Exploring early indications of heart disease is challenging in today's society. It may lead to death if not detected early. Early identification of cardiac disease in remote, rural, and semi-urban locations in developing nations can be greatly aided by an accurate decision support system (DSS). To assist in heart-related disease detection at an early stage, this system offers a DSS which uses artificial learning techniques using the patient's clinical details. A hybridized class balancing methodology using the chi2 feature selection algorithm, random oversampling, and undersampling techniques were used to find the suitable features from the presented dataset. Standard scalar approaches have also been utilized for data preprocessing. In the last stage of developing the suggested Artificial Intelligence (AI) system, the system used support vector machines (SVM), naive Bayes, random forest classifiers, logistic regression, and improved Artificial Neural Network (ANN) classifiers. Tests were conducted on the Python-based simulation environment to evaluate the proposed system. Evaluation of the system is completed using the Cleveland heart disease dataset by the machine repository at UCI. A 96.74% accuracy rate was reached, which is better than some previously published models for heart-related disease prediction.