Investigating Liver Disease Machine Learning Prediction Performance through Various Feature Selection Methods - read online

Aug 4, 2026

Upload by Quinn

Given the rising prevalence and substantial global health burden of liver diseases, accurate predictive modeling is critical for early detection and effective treatment planning. The study systematically examines how four feature selection approaches—regular, ANOVA, univariate, and model-based—affect the performance of multiple machine learning classifiers used for liver disease prediction. Results show feature selection has a significant but varying impact on accuracy, with ANOVA plus multi-layer perceptron reaching the best score (0.801724) and univariate best for decision forest (0.741379). Model-based selection can reduce performance, while SVC remains robust across methods.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages14

Reading Time35 min

AccessFree to download

Introduction

Liver disease burden and need for prediction

Biomarkers and clinical data

Role of machine learning in diagnosis

Impact of irrelevant features

Method Overview

Feature selection techniques

Classifiers evaluated

Matrik: Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer Vol. 24, No. 3, July 2025, pp. 507∼520 ISSN: 2476-9843, accredited by Kemenristekdikti, Decree No: 10/C/C3/DT.05.00/2025 DOI: 10.30812/matrik.v24i3.4531 ❒ 507 | Investigating Liver Disease Machine Learning Prediction Performance through Various Feature Selection Methods
Ahmad Zein Al Wafi , Febry Putra Rochim , Veda Bezaleel
Universitas Negeri Semarang, Semarang, Indonesia | | | --- | --- | | Article Info
Article history:
Received October 11, 2024 Revised June 26, 2025 Accepted July 1, 2025
Keywords:
Feature Selection;
Liver Disease Prediction; Machine Learning. | ABSTRACT
Given the increasing prevalence and significant health burden of liver diseases globally, improving the accuracy of predictive models is essential for early diagnosis and effective treatment. The purpose of the study is to systematically analyze how different feature selection methods impact the performance of various machine learning classifiers for liver disease prediction. The research method involved evaluating four distinct feature selection techniques—regular, analysis of variance (ANOVA), univariate, and model-based—on a suite of classifiers, including decision forest, decision tree, support vector classifier, multi-layer perceptron, and linear discriminant analysis. The result revealed a significant and variable impact of feature selection on model accuracy. Notably, the ANOVA method paired with the multi-layer perceptron achieved the highest accuracy of 0.801724, while the univariate method was optimal for the decision forest classifier (0.741379) . In contrast, model-based selection often degraded performance, particularly for the decision tree classifier, likely due to the introduction of noise and overfitting. The support vector classifier, however, demonstrated robust and consistent accuracy across all selection techniques. These findings underscore that there is no universally superior featureselection method; instead, optimal predictive performance hinges on tailoring the selection technique to the specific machine learning model. This study contributes practical, evidence-based insights into the critical interplay between feature selection and model choice in medical data analysis, offering a guide for improving classification accuracy in liver disease prediction. Future work should explore more sophisticated and hybrid feature selection methods to enhance model performance further.
Copyright ©2025 The Authors.
This is an open access article under the CC BY-SA license.
| | Corresponding Author:
Febry Putra Rochim, +6281225777701,
Faculty of Engineering, Computer Engineering Department,
State University of Semarang, Semarang, Indonesia,
Email: [febry.putra@mail.unnes.ac.id](febry.putra@mail.unnes.ac.id) | | | How to Cite:
A. Z. A. Wafi, F. P. Rochim, and V. Bezaleel,, ”Investigating Liver Disease Machine Learning Prediction Performance through Various Feature Selection Methods”, MATRIK: Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer, Vol. 24, No. 3, pp. 505-518, July, 2025, doi:10.30812/matrik.v24i3.4531 .
This is an open access article under the CC BY-SA license ([https://creativecommons.org/licenses/by-sa/4.0/](https://creativecommons.org/licenses/by-sa/4.0/)) | | Journal homepage: [https://journal.universitasbumigora.ac.id/index.php/matrik](https://journal.universitasbumigora.ac.id/index.php/matrik) 1. INTRODUCTION Liver disease poses a significant health burden globally, with its prevalence steadily rising over the past decades [1] . Cirrhosis or liver damage is a significant contributor to both death and illness globally, ranking as the 11th major cause of death and the 15th largest cause of morbidity in 2016 [2] . Early detection and accurate prediction of liver disease play pivotal roles in effective patient management, treatment planning, and ultimately, in reducing mortality rates associat

FAQs

What is the main goal of the study on liver disease prediction models?

To analyze how different feature selection methods influence the performance of various machine learning classifiers for liver disease prediction.

Which feature selection method achieved the highest accuracy, and with which classifier?

The ANOVA method combined with the multi-layer perceptron achieved the highest accuracy of 0.801724.

Why can model-based feature selection degrade performance for some classifiers?

It may introduce noise and increase overfitting, leading to lower accuracy, especially for the decision tree classifier.

Aug 4, 2026

Upload by Quinn