Heart Failure Prediction Using Artificial Intelligence Methods

Heart disease is a significant global health concern, and accurate diagnosis is essential for the effective treatment. In this study, we focus on utilizing the Support Vector Machine (SVM) algorithm with the radial basis function (RBF) kernel to develop a heart disease classification model. The SVM model with the RBF kernel achieves an accuracy of 91.85%, with precision, recall, and F1-score metrics supporting the model's ability to correctly identify positive instances. To support our results, a 5-mean clustering method classified the data. We apply K-means clustering analysis method to reveal hidden patterns within the data. K-means clustering is an unsupervised learning technique that allows the algorithm to process unlabeled and unclassified data independently. The dataset is meticulously preprocessed to handle missing values, categorical variables, and feature scaling, followed by feature extraction to optimize clustering performance. The application of K-means clustering offers valuable insights into potential heart disease subgroups, supporting early detection and personalized care strategies with 84% accuracy.