Comparison of Naïve Bayes, K-Nearest Neighbors, and Decision Tree Methods for Classifying Heart Disease Risk Factors

Ahmad Jihad Al Fayed
Surya Darma
Zailani Sinabariba
Surya Maruli P Pardede

Journal of Computer Science and Research
Vol. 3 No. 3 (2025): July: Health Science Informatic

Heart disease is the leading cause of death and poses a major challenge to global health systems. The classification of heart disease risk factors is crucial for preventing serious indications, but the challenge is that detection of this disease is often hampered because the classification process is not yet sufficiently accurate. This study aims to develop a heart disease risk classification model using a machine learning approach on a 2025 dataset consisting of 6025 patient data with 14 features. After going through the data collection stage and determining the attributes for comparing the performance of machine learning algorithms (Naive Bayes, K-Nearest Neighbors, and Decision Tree), it was found that the Decision Tree algorithm provided the best performance with an accuracy of 86%, followed by the K -Nearest Neighbors algorithm with an accuracy of 78% and the Naive Bayes algorithm with an accuracy of 76%.