An Improved K-NN Algorithm and Bagging for Liver Disease Classification

Wardhani, Anindya Khrisna ((Scopus ID: 55878271900, Vivekananda Institute of Professional Studies))
Lakhmudien, Lakhmudien (Politeknik Rukun Abdi Luhur)
Putri, Astrid Novita (Universitas Semarang)
Ashour, Salim Fathi Salim (Elmergib University)

Telematika
Vol 15, No 2: August (2022)

The function of the liver is to detoxify toxins in the human body and control cholesterol and fat in the human body. If the liver is damaged, health will be disturbed, even death. A lot of data on the liver disease can be used to predict liver disease. This study aims to improve the accuracy of liver disease classification using K-NN and bagging methods. The experimental results in this study are the bagging method can improve the performance accuracy of the K-NN prediction model even though it is based on the T-test even though there is only a slight change in accuracy. In this study, the accuracy value using the K-NN method was 78.56%. For the highest accuracy value of 99.83% using the K-NN model which is integrated with bagging. From the results of experiments carried out in this study, the K-NN model with bagging can certainly improve performance on the prediction model of liver disease classification. So that the predictions made can be more accurate and can be used to predict liver disease.