Skip to content
Research Article Open access CC BY 4.0

Comparative Analysis of Machine Learning Algorithms for Liver Disease Prediction: SVM, Logistic Regression, and Decision Tree

Venugopal Reddy Modhugu, Sivakumar Ponnusamy

Asian Journal of Research in Computer Science · pp. 188–201 · Published 14 May 2024

10.9734/ajrcos/2024/v17i6467

Abstract

This study compares Support Vector Machine (SVM), Logistic Regression, and Decision Tree algorithms for liver disease prediction using a dataset sourced from Kaggle, comprising 20,000 training records and approximately 1,000 test records. The research evaluates the algorithms based on performance metrics, including accuracy, precision, recall, and F1-score. SVM emerged as the most effective model with an accuracy of 85%, followed by Logistic Regression with 82% and Decision Tree with 79%. The findings underscore the significance of algorithm selection in healthcare applications and highlight SVM's potential for early detection and intervention in liver disease cases, paving the way for improved patient outcomes and healthcare management. Future work will focus on refining the algorithms and validating the results with larger and more diverse datasets to enhance predictive accuracy and robustness further.

Liver disease prediction machine learning algorithms Support Vector Machine (SVM) logistic regression decision tree

References (22)

  1. 1 Prediction of fatty liver disease using machine learning algorithms [DOI]
  2. 2 A Revised Model for End-Stage Liver Disease Optimizes Prediction of Mortality Among Patients Awaiting Liver Transplantation [DOI]
  3. 3 Performance analysis of classification algorithms on early detection of liver disease [DOI]
  4. 4 Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm [DOI]
  5. 5 Machine learning enables new insights into genetic contributions to liver fat accumulation [DOI]
  6. 6 Software-based Prediction of Liver Disease with Feature Selection and Classification Techniques [DOI]
  7. 7 A comparative analysis of boosting algorithms for chronic liver disease prediction [DOI]
  8. 8 Monitoring multistage healthcare processes using state space models and a machine learning based framework [DOI]
  9. 9 Multiclass liver disease prediction with adaptive data preprocessing and ensemble modeling [DOI]
  10. 10 Noninvasive Assessment of Liver Fibrosis: Current and Future Clinical and Molecular Perspectives [DOI]
  11. 11 Nutrient sensor–mediated programmed nonalcoholic fatty liver disease in low birthweight offspring [DOI]
  12. 12 Machine learning-based energy monitoring method applied to the HVAC systems electricity demand of an Italian healthcare facility [DOI]
  13. 13 A fusion of machine learning algorithms and traditional statistical forecasting models for analyzing American healthcare expenditure [DOI]
  14. 14 Application of the Revised Cardiac Risk Index to the Model for End-Stage Liver Disease Score Improves the Prediction of Cardiac Events in Patients Undergoing Liver Transplantation [DOI]
  15. 15 Improving the Prediction of Mortality in the High Model for End-Stage Liver Disease Score Liver Transplant Recipient: A Role for the Left Atrial Volume Index [DOI]
  16. 16 Utilizing Natural Language Processing (NLP) to Accurately Identify Fatty Liver Disease [DOI]
  17. 17 Vitamin-d receptor (VDR) polymorphism and types of HBV related liver disease along with an SVM based disease prediction model [DOI]
  18. 18 The development of the diabetes liver fibrosis score: A new prediction model to detect advanced fibrosis in diabetics with nonalcoholic fatty liver disease [DOI]
  19. 19 An Automatic Grading Method of Liver Cirrhosis from Abdominal CT Images [DOI]
  20. 20 Classification of Liver Cirrhosis with Statistical Analysis of Texture Parameters
  21. 21 587 MACHINE LEARNING MODEL CORRECTLY IDENTIFIES PATIENTS WITH ADVANCED LIVER FIBROSIS WHICH ARE INDETERMINATE BY FIB-4 INDEX IN NON-ALCOHOLIC FATTY LIVER DISEASE. [DOI]
  22. 22 Patient-Specific Genome-Scale Metabolic Models for Individualized Predictions of Liver Disease [DOI]

Cited by 80

Comparative Study of Logistic Regression and K-Nearest Neighbor for Heart Disease Prediction

Abyan Ozaga, Murien Nugraheni, Widodo · 2024 7th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · 2024

Machine learning techniques in hepatic encephalopathy: a scoping review

Fatemeh Kiani, Farkhondeh Asadi, Azamossadat Hosseini · BMC Medical Informatics and Decision Making · 2025

Machine Learning Strategies for Classification of Liver Cirrhosis

K.Amrutha Varshini, G.Jayalakshmi, K.Pramodhini · 2025 International Conference on Intelligent Computing and Control Systems (ICICCS) · 2025

Accurate Diabetes Prediction Using a Robust Framework Based on a Hard-Voting Classifier

Mohammed S. Hashim · Journal of Information Systems Engineering and Management · 2025

A Systematic Review on Machine Learning and Deep Learning Methods for Predicting Liver Disease: Focus on Explainable AI

Koteswara Rao Makkena, Karthika Natarajan · Information Systems Engineering and Management · 2025

Explainability enhanced liver disease diagnosis technique using tree selection and stacking ensemble-based random forest model

Mohammad Mamun, Safiul Haque Chowdhury, Muhammad Minoar Hossain · Informatics and Health · 2025

Research on the Application of Logistic Regression Algorithm in Disease Classification Using Steepest Descent Method for Parameter Optimization

Meirui Song, Rujuan Huang, DuoDuo Ding · 2024 3rd International Conference on Health Big Data and Intelligent Healthcare (ICHIH) · 2024

Artificial Neural Networks-Based Machine learning for Analysis of Sub-surface Water quality

B.Anuradha, Sheena. A. D, Hemamalini. J · 2025 International Conference on Data Science, Agents & Artificial Intelligence (ICDSAAI) · 2025

Showing 20 of 80 known citations — external sources report more than can currently be individually listed.

Article metrics

Real usage data collected on this platform.

25

Page views

0

PDF downloads

2

Outbound clicks

80

Citations

Views over time

Views by country

Approximate, from request IP at view time — not citizenship or institution. Countries with fewer than 5 views are grouped as "Other".

Traffic sources

Referring site, by host.

Views and downloads exclude known bots/crawlers. Citations combines this platform's own DOI-resolved index with each external source's own reported total — see Cited by above for individually listed citing works. Last refreshed 0 seconds ago.