Detection of Cardiovascular Disease Using Extreme Learning Machine and Artificial Neural Network

Early detection and treatment of heart disease are crucial for improving patient outcomes and lowering healthcare costs since it is a prominent factor in fatalities. Worldwide. This research uses patient characteristics to analyze machine learning models to detect and forecast the risk of diseases involving the human heart. Age, sex, cholesterol, and blood pressure were just a few of the 14 distinct factors that comprised the collection, including 270 patient records. This study compared artificial neural networks (ANN) and Extreme Learning Machines (ELM) and obtained 98.77% and 86.42% accuracy, respectively. ANNs are versatile for different heart disease patterns because they are excellent at capturing complex nonlinear correlations and feature learning. Conversely, ELM is relatively less complicated to implement and offers a much faster training pace than other traditional ML techniques.