Heart attacks are one of the most severe health concerns in the modern world. Early detection of this disease is crucial because it has the potential to save more than 17.9 million lives annually. Heart attacks are a form of coronary artery disease which occurs when there is inadequate oxygenation in one or more heart regions. Several health factors and habits influence the risk of heart disorders. In recent years, this scientific field has received a lot of interest. While forecasting cardiac diseases has always been challenging and crucial for medical professionals, doing so at an early stage will benefit people everywhere so that appropriate preventative measures can be taken before the condition becomes severe. Over time, machine learning tools have been applied to the healthcare industry to forecast disease accurately. This paper studies K-Nearest Neighbor (KNN) and Support Vector Machine (SVM) models to predict cardiac attacks accurately. The effectiveness of these models is assessed using K-Folds cross-validation and evaluation metrics like accuracy, precision, recall, F1 Score, and AUC. The KNN algorithm is proven more efficient and precise than SVM, with an accuracy score of 90.3% compared to SVM's only 87%.

SVM, KNN, Performance Metrics, Heart Attack Prediction