A Machine Learning-Based Framework for Accurate and Early Diagnosis of Liver Diseases - A Comprehensive Study on Feature Selection, Data Imbalance, and Algorithmic Performance

Aug 4, 2026

Upload by Eliana

Liver diseases such as cirrhosis and fibrosis require effective, early, and accurate identification to prevent progression and fatal outcomes. This research performs a systematic protocol-based review of 58 studies (2015–2023) and answers six research questions on machine-learning approaches. It identifies suitable feature selection methods, data-imbalance handling techniques, accurate algorithms, and dataset resources with characteristics, then proposes the MaLLiDD framework and validates it on three datasets, achieving reported accuracies up to 99.56%.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages29

Reading Time1 h 13 min

AccessFree to download

Introduction

Problem background and clinical motivation

Role of machine learning in early diagnosis

Related approaches and need for improved frameworks

Literature review and research questions

Systematic protocol-based review process

Feature selection and data imbalance research questions

Algorithms, datasets, and feature importance

Proposed framework and validation

MaLLiDD framework design

Experimental setup and datasets

Classification results and performance evaluation

Conclusion

Wiley International Journal of Intelligent Systems Volume 2024, Article ID 6111312, 29 pages [https://doi.org/10.1155/2024/6111312](https://doi.org/10.1155/2024/6111312) Research Article A Machine Learning-Based Framework for Accurate and Early Diagnosis of Liver Diseases: A Comprehensive Study on Feature Selection, Data Imbalance, and Algorithmic Performance Attique Ur Rehman , 1,2,3 Wasi Haider Butt , 1 Tahir Muhammad Ali ,2 Sabeen Javaid ,3 Maram Fahaad Almufareh ,4 Mamoona Humayun ,5 Hameedur Rahman ,6 Azka Mir ,3 and Momina Shaheen 5 1 Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences & Technology, Islamabad, Pakistan 2 Department of Computer Science, Gulf University for Science and Technology, Mubarak Al-Abdullah, Kuwait 3 Department of Software Engineering, University of Sialkot, Sialkot, Pakistan 4 Department of Information Systems, College of Computer and Information Sciences, Jouf University, Al Jouf, Saudi Arabia 5 School of Arts Humanities and Social Sciences, University of Roehampton, London SW15 5PJ, UK 6 Department of Computer Games Development, Faculty of Computing & AI, Air University PAF Complex, E9, Islamabad, Pakistan Correspondence should be addressed to Momina Shaheen; [momina.shaheen@roehampton.ac.uk](momina.shaheen@roehampton.ac.uk)[ ](momina.shaheen@roehampton.ac.uk)Received 22 December 2023; Revised 7 May 2024; Accepted 29 May 2024 Academic Editor: Said El Kafhali Copyright © 2024 Attique Ur Rehman et al. Tis is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Te liver is the largest organ of the human body with more than 500 vital functions. In recent decades, a large number of liver patients have been reported with diseases such as cirrhosis, fbrosis, or other liver disorders. Tere is a need for efective, early, and accurate identifcation of individuals sufering from such disease so that the person may recover before the disease spreads and becomes fatal. For this, applications of machine learning are playing a signifcant role. Despite the advancements, existing systems remain inconsistent in performance due to limited feature selection and data imbalance. In this article, we reviewed 58 articles extracted from 5 diferent electronic repositories published from January 2015 to 2023 . After a systematic and protocol-based review, we answered 6 research questions about machine learning algorithms. Te identifcation of efective feature selection techniques, data imbalance management techniques, accurate machine learning algorithms, a list of available data sets with their URLs and characteristics, and feature importance based on usage has been identifed for diagnosing liver disease. Te reason to select this research question is, in any machine learning framework, the role of dimensionality reduction, data imbalance management, machine learning algorithm with its accuracy, and data itself is very signifcant. Based on the conducted review, a framework, machine learning-based liver disease diagnosis (MaLLiDD), has been proposed and validated using three datasets. Te proposed framework classifed liver disorders with 99.56%, 76.56%, and 76.11% accuracy. In conclusion, this article addressed six research questions by identifying efective feature selection techniques, data imbalance management techniques, algorithms, datasets, and feature importance based on usage. It also demonstrated a high accuracy with the framework for early diagnosis, marking a signifcant advancement. 1. Introduction Te functionality of the liver is strongly afected by viral diseases that cause infammation. Such a disease can get severe and be shown as a fatal one. Liver disease has been observed as a common clinical disorder that is being increased in parallel with diabetes

FAQs

Why is early and accurate liver disease diagnosis important?

Early identification helps patients recover before diseases spread and become fatal. The paper emphasizes high prevalence and poor prognosis for conditions like liver cancer.

What key limitations in existing machine-learning systems are addressed?

The review highlights inconsistent performance caused by limited feature selection and data imbalance, motivating a more comprehensive framework.

How does the proposed MaLLiDD framework perform?

The framework is validated using three datasets and reports classification accuracies of 99.56%, 76.56%, and 76.11% for liver disorder identification.

Aug 4, 2026

Upload by Eliana