Perbandingan Dalam Memprediksi Penyakit Liver Menggunakan Algoritma Naïve Bayes Dan K-Nearest Neighbor

Abstract

Along with the rapid development of information technology, and also the increasing need for information in various fields including health sector. Based on data from the World Health Organization (WHO), chronic hepatitis B attacks 300 million people in the world including Southeast Asia and Africa which causes the death of more than 1 million people each year. So far, a lot of data in the hospital has not been used, even though this data can be used to predict liver disease if used. The purpose of this study was to determine the comparison of the accuracy value of the Naïve Bayes algorithm and K-Nearest Neighbor. One of the classifications is to use the Naïve Bayes and K-Nearest Neighbor algorithms and use the Rapid Miner tools in the tests used. The results of this study indicate that the Naïve Bayes algorithm has a higher accuracy rate of 84.00% in diagnosing liver disease compared to the K-Nearest Neighbor algorithm which only gets a value of 80.57%. From this research it can be concluded that the Naïve Bayes algorithm is 3.43% greater than K-Nearest Neighbor.