Feature Selection Information Gain pada Klasifikasi Pasien Penyakit Jantung (Heart Disease)

Abstract

Heart disease, also known as cardiovascular disease, is a condition where there is a blockage or narrowing of blood vessels that can lead to heart attack, chest pain, or stroke. It needs appropriate medical treatment because this disease can be the cause of death. Data mining methods are helpful in diagnosing and treating heart disease. Data mining methods can play a major role in the process of improving the quality of care for heart disease patients, providing valuable information for informed decision-making regarding prevention and treatment. The data analysis process uses classification algorithms, namely Decision Tree (C4.5), Naive Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF) combined with feature selection information gain method. The results show that data mining methods are very useful in diagnosing and treating heart disease. The highest percentage of correct classifications for both models before and after the implementation of feature selection information gain was obtained by the RF algorithm, which amounted to 95.71%. However, the implementation of the feature selection information gain method in this study did not contribute significantly to improving the classification quality of each algorithm used.