Perbandingan Kinerja Akurasi Model Mesin Learning Untuk Prediksi Penyakit Jantung

Abstract

This research aims to comprehensively analyze heart disease-related data through Exploratory Data Analysis (EDA), identification of correlations between numerical variables, and cluster analysis to uncover patterns in the data. Furthermore, using various machine learning algorithms, such as Logistic Regression, Support Vector Classifier, Decision Tree Classifier, Random Forest Classifier, K-Nearest Neighbors, and Gaussian Naive Bayes, a heart disease prediction model was built. The model evaluation shows that Naive Bayes has the highest test accuracy of 90%, followed by RandomForestClassifier and KNeighborsClassifier which have 85% test accuracy. These findings indicate a good ability to predict heart disease, but further analysis is needed to ensure good generalization to unseen data. This research makes an important contribution to the development of heart disease prediction models and can support early detection and appropriate intervention strategies.