Heart disease has become a global health issue that can threaten anyone, regardless of age. Numerous research efforts have been made to develop classification methods that can aid in diagnosing heart disease. In this study, we compared two classification methods, namely K-Nearest Neighbor (KNN) and Decision Tree, by applying Principal Component Analysis (PCA) technique to the heart disease classification. The dataset used contains relevant clinical attributes. After analyzing the dataset and performing data preprocessing, we applied PCA to reduce the dataset's dimensions. PCA models with KNN and Decision Tree were implemented and evaluated using performance metrics such as Confusion Matrix, F1 Score, and Accuracy. The analysis results showed that the PCA model with Decision Tree outperformed the PCA model with KNN in terms of accuracy. The Decision Tree model successfully classified all data correctly, while KNN had some misclassifications. This research recommends using the PCA model with Decision Tree for heart disease classification with the best performance. However, further research with larger datasets is needed for a deeper understanding
Copyrights © 2023