Comparative Classification of Hepatitis C Disease Using Naïve Bayes and Random Forest with SMOTE-Based Class Balancing

Salsavana, Ida Oktavia, Hariyadi, M. Amin ORCID: https://orcid.org/0000-0001-9327-7604 and Fresy, Nugroho (2026) Comparative Classification of Hepatitis C Disease Using Naïve Bayes and Random Forest with SMOTE-Based Class Balancing. Armada Jurnal Penelitian Multidisiplin, 4 (6). pp. 2319-2331. ISSN 2964-2981

Preview

Text ID2961-06-2026-ARD.pdf Download (622kB) | Preview

Abstract

Abstract: Hepatitis C is a liver disease caused by the Hepatitis C Virus (HCV) that can lead to serious complications such as cirrhosis, liver failure, and liver cancer. Early and accurate detection is crucial to improving treatment outcomes and patient quality of life. This study compares the performance of Naïve Bayes and Random Forest algorithms in classifying Hepatitis C disease using clinical data from the UCI Machine Learning Repository, consisting of 615 patient records. The preprocessing stage included data cleaning, data transformation, and class balancing using the Synthetic Minority Over-sampling Technique (SMOTE) to address class imbalance. The dataset was divided into training and testing sets at an 80:20 ratio. Results show that Random Forest achieved an accuracy of 99.06%, precision of 0.99, recall of 0.98, and F1-score of 0.99, outperforming Naïve Bayes which obtained an accuracy of 84.06%. Feature importance analysis identified AST, ALT, GGT, Age, and Albumin as the most significant clinical predictors. The combination of Random Forest and SMOTE proves to be a highly effective approach for Hepatitis C classification and holds strong potential to support accurate clinical decision-making in early disease detection.

Abstrak: Hepatitis C merupakan penyakit hati yang disebabkan oleh Virus Hepatitis C (HCV) dan dapat berkembang menjadi komplikasi serius seperti sirosis, gagal hati, dan kanker hati. Deteksi dini yang akurat sangat penting untuk meningkatkan keberhasilan pengobatan dan kualitas hidup pasien. Penelitian ini membandingkan kinerja algoritma Naïve Bayes dan Random Forest dalam klasifikasi penyakit Hepatitis C menggunakan data klinis dari UCI Machine Learning Repository yang terdiri atas 615 data pasien. Tahap prapemrosesan meliputi pembersihan data, transformasi data, dan penyeimbangan kelas menggunakan metode Synthetic Minority Over-sampling Technique (SMOTE). Dataset dibagi dengan rasio 80:20 untuk data latih dan data uji. Hasil eksperimen menunjukkan bahwa Random Forest menghasilkan akurasi 99,06%, precision 0,99, recall 0,98, dan F1-score 0,99, jauh melampaui Naïve Bayes yang memperoleh akurasi 84,06%. Analisis feature importance mengidentifikasi AST, ALT, GGT, Usia, dan Albumin sebagai prediktor klinis paling signifikan. Kombinasi algoritma Random Forest dan SMOTE terbukti menjadi pendekatan yang sangat efektif dalam klasifikasi Hepatitis C dan berpotensi besar mendukung pengambilan keputusan klinis yang akurat untuk deteksi dini penyakit

Item Type:	Journal Article
Keywords:	Hepatitis C, Ketidakseimbangan Kelas, Naïve Bayes, Random Forest, SMOTE
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080105 Expert Systems
Divisions:	Graduate Schools > Magister Programme > Graduate School of Informatics Engineering
Depositing User:	Mokhamad Amin Hariyadi
Date Deposited:	13 Jul 2026 09:24

Downloads

Origin of downloads

Actions (login required)

View Item