Arief, Rizza Muhammad ORCID: https://orcid.org/0009-0007-1837-6179 and Susanto, Divira Salsabiil (2024) Pemodelan Deteksi Dini Gejala Penyakit Sirosis Hati Menggunakan Machine Learning dengan Pendekatan Supervised Learning. Jurnal RESTIKOM : Riset Teknik Informatika dan Komputer, 6 (2). pp. 223-239. ISSN P-ISSN : 1979-8415; E-ISSN : 2714-8025

Preview	Text Pemodelan Deteksi Dini Gejala Penyakit Sirosis Hati.pdf Download (1MB) | Preview
Preview	Text Hasil Cek Plagiasi_Pemodelan Deteksi Dini Gejala Penyakit Sirosis Hati.pdf Download (1MB) | Preview

Abstract

Cirrhosis of the liver is a serious consequence of chronic hepatitis that can lead to fatal complications. Early detection of liver cirrhosis is crucial to improving prognosis and reducing the risk of complications. However, its symptoms are often nonspecific, making diagnosis difficult at an early stage. This study utilizes a dataset from the Mayo Clinic to analyze liver cirrhosis using three machine learning models: K-Nearest Neighbors (KNN), Naive Bayes, and Support Vector Machine (SVM). The results indicate that the KNN model has the highest accuracy (92.04%), demonstrating effective capability in classifying liver cirrhosis. Based on the confusion matrix, KNN accurately classifies patients with liver cirrhosis, with few errors in identifying different classes. In comparison, the Naive Bayes model shows lower performance with an accuracy of 52.14%, while SVM has an accuracy of 81.88%. In the context of early detection of liver cirrhosis, the KNN model stands out as the best choice due to its high accuracy and ability to correctly classify patients. Preprocessing steps such as normalization and one-hot encoding also play a crucial role in improving model performance. These findings provide an important foundation for the development of better early detection systems for liver cirrhosis, enabling timely medical interventions and improving patient prognosis.

Actions (login required)

View Item