Skripsi
KLASIFIKASI PENYAKIT JANTUNG BERBASIS SELEKSI FITUR CHI-SQUARE DAN MACHINE LEARNING
Heart disease is one of the leading causes of death worldwide, making accurate early detection methods essential. Machine learning can be used to classify patients conditions, but data imbalance and feature selection can affect model performance. This study applied Chi-Square feature selection and the Synthetic Minority Over-sampling Technique (SMOTE) to 918 patient records with 11 clinical attributes, resulting in 9 key features. Classification was performed using Random Forest, Support Vector Machine (SVM), and K-Nearest Neighbour (KNN). The results show that Random Forest performed best with an accuracy of 93.48%, indicating its ability to handle complex and imbalanced data compared to other algorithms. Thus, the methods used are capable of improving model performance in the early detection of heart disease and supporting clinical decision-making.
No other version available