Hybrid Genetic Algorithm and Support Vector Machine for Hyperparameter Optimization in Liver Disease Classification

Liver disease remains a significant health concern in Indonesia, making early detection essential for reducing the risk of complications and improving treatment outcomes. Advances in machine learning have enabled the automated classification of diseases based on patients’ clinical data. Support Vector Machine (SVM) is a widely used classification algorithm; however, its performance can be affected by hyperparameter selection and class imbalance. This study employed the Indian Liver Patient Dataset (ILPD), which initially contained 583 records. Following data preprocessing, including data selection, cleaning, transformation, and standardization, 570 records remained after duplicate removal. Model performance was evaluated using stratified 10-fold cross-validation based on accuracy, precision, recall, and F1-score. Two classification approaches were compared: standard SVM and SVM optimized using a Genetic Algorithm (SVM-GA). The results showed that the SVM-GA model achieved an accuracy of 70.88%, precision of 72.14%, recall of 96.31%, and F1-score of 82.49%. In comparison, the standard SVM model achieved an accuracy of 70.18%. These findings indicate that GA-based hyperparameter optimization yielded a modest improvement in classification accuracy on the ILPD dataset, although improvements were not observed across all evaluation metrics.

Authors

Institutions

Publication Details

Journal
JOINS (Journal of Information System)
Published
2026-11-12
DOI
https://doi.org/10.33633/joins.v11i2.17703
Primary Topic
Artificial Intelligence in Healthcare
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Hybrid Genetic Algorithm and Support Vector Machine for Hyperparameter Optimization in Liver Disease Classification

Taghfirul Azhima Yoga Siswa, Muhammad Ridwan, Maliq Yazid Imani
JOINS (Journal of Information System)
Artificial Intelligence in Healthcare
article

Hybrid Genetic Algorithm and Support Vector Machine for Hyperparameter Optimization in Liver Disease Classification

Taghfirul Azhima Yoga Siswa, Muhammad Ridwan, Maliq Yazid Imani
article en

Abstract

Liver disease remains a significant health concern in Indonesia, making early detection essential for reducing the risk of complications and improving treatment outcomes. Advances in machine learning have enabled the automated classification of diseases based on patients’ clinical data. Support Vector Machine (SVM) is a widely used classification algorithm; however, its performance can be affected by hyperparameter selection and class imbalance. This study employed the Indian Liver Patient Dataset (ILPD), which initially contained 583 records. Following data preprocessing, including data selection, cleaning, transformation, and standardization, 570 records remained after duplicate removal. Model performance was evaluated using stratified 10-fold cross-validation based on accuracy, precision, recall, and F1-score. Two classification approaches were compared: standard SVM and SVM optimized using a Genetic Algorithm (SVM-GA). The results showed that the SVM-GA model achieved an accuracy of 70.88%, precision of 72.14%, recall of 96.31%, and F1-score of 82.49%. In comparison, the standard SVM model achieved an accuracy of 70.18%. These findings indicate that GA-based hyperparameter optimization yielded a modest improvement in classification accuracy on the ILPD dataset, although improvements were not observed across all evaluation metrics.

JOINS (Journal of Information System)Vol. 11(2)
Universitas Muhammadiyah Kalimantan Timur (ID)
Artificial Intelligence in Healthcare
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon