Liver cirrhosis prediction using logistic regression, naïve bayes and KNN

Fahmudur Rahman 1, *, Denesh Das 2, 3, Anhar Sami 4, 5, Priya Podder 6 and Daniel Lucky Michael 7

1 Northern International Medical College and Hospital, Dhanmondi, Dhaka 1209, Bangladesh.
2 Department of Electrical and Computer Engineering, Lamar University, Beaumont, Texas 77710, USA.
3 Department of Electrical and Electronics Engineering, Southern University Bangladesh, Chattogram, Bangladesh.
4 Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, MO 65401, USA.
5 Electrical and Computer Engineering, Altinbas University, Istanbul, Turkey.
6 Dhaka National Medical College, Dhaka 1100, Bangladesh.
7 Department of Electrical Engineering, School of Engineering, San Francisco Bay University, Fremont, CA 94539, USA.
 
Research Article
International Journal of Science and Research Archive, 2024, 12(01), 2411–2420.
Article DOI: 10.30574/ijsra.2024.12.1.1030
Publication history: 
Received on 28 April 2024; revised on 04 June 2024; accepted on 07 June 2024
 
Abstract: 
Liver cirrhosis, often a symptomless blood-borne disease in its early stages, presents significant diagnostic and treatment challenges. As the disease advances, these difficulties only increase. This study introduces an artificial intelligence system based on machine learning to aid healthcare providers in the early detection of liver cirrhosis. With this aim, three distinct predictive models have been developed using a variety of physiological metrics and machine learning techniques including Logistic Regression (LR), Naïve Bayes and KNN Classification. Among these, LR emerges as the most effective, achieving an accuracy of approximately 85%. The models are developed using the openly accessible Liver Cirrhosis data dataset.
 
Keywords: 
Liver Cirrhosis; Machine Learning; Logistic Regression; Naïve Bayes and KNN
 
Full text article in PDF: 
 
Copyright information: 

Copyright © 2024 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0