Skip to content
SDGs Center UDINUS

Evidence record · UDINUS · SDGs

Comparison of Naïve Bayes and KNN Algorithms to Understand Hepatitis

Rektorat UDINUS 2020 Published 2026-10-30

Evidence record · UDINUS · SDGs

Unit
Rektorat UDINUS
Period
2020
Goals
Record
2a20774e-a390-4cc0-a17e-a8aabe2fa779
Published
2026-10-30

Universitas Dian Nuswantoro (UDINUS), with researchers Alfyani, Resty and Muljono as activity participants, conducted a study comparing the Naïve Bayes and K-Nearest Neighbor (KNN) algorithms for hepatitis classification and prediction. The activity used a technology and information-based approach to examine hepatitis, a disease that attacks the liver and is caused by a virus.

The study explains that the liver functions to neutralize toxins in the blood and regulate the composition of blood containing fat, protein, sugar, and other substances. Hepatitis can be known through a laboratory test on blood. To support classification and prediction, the study used public data from the UCI Repository. The dataset contained 155 data records and 19 attributes, including Age, Gender, Steroids, Antivirus, Fatigue, Malaise, Anorexia, Big Heart, Heart Company, Spleen, Spiders, Ascites, Varicose, Bilirubin, Alk Phosphate, Shot, Albumin, Protime, Histology, and Class as the predictive attribute.

The activity compared the performance of the Naïve Bayes and KNN algorithms. Experiments used a confusion matrix to determine accuracy, precision, and recall. The reported accuracy for the Naïve Bayes algorithm was 74.19%, with an average error level of 25.81%. The K-Nearest Neighbor algorithm produced an average accuracy value of 54.84% and an average error level of 45.18%. The study also stated that the K-Nearest Neighbor algorithm increased the accuracy value and the average error value from previous studies.

Through this activity, UDINUS contributed a classification and prediction comparison concerning hepatitis using public data and a confusion-matrix evaluation. The findings provide an institutional example of research addressing a health-related topic through information technology methods and support the stated purpose concerning hepatitis understanding.

Reference https://www.scopus.com/pages/publications/85096852415?origin=resultslist