Prediction of heart disease using grey wolf optimization-based extreme learning machine

Cardiovascular disease (CVD) is increasingly becoming a substantial global health threat. Early identification and prediction of cardiovascular disease, as well as other cardiac illnesses, has the potential to save many lives. This demands a thorough assessment of clinical data. To improve their diagnostic accuracy, healthcare providers must use predictive machine learning algorithms. This study examined multiple machine learning heart disease detection methods using the UC Irvine Cleveland dataset. The study comprised 303 patient records with 14 clinical criteria. Data was split 80% training and 20% testing. This study investigates how machine learning can predict heart disease on the UC Irvine Cleveland dataset. K-NN achieved 86.89% accuracy, SVM 88.52%, ELM 95.08%, and GWO-ELM excelled with 96.72% accuracy, showcasing superior classification.