Classification of liver disease diagnosis: a comparative study

Medical Data Mining (MDM) is one of the most critical aspects of automated disease diagnosis and disease prediction. MDM involves developing data mining algorithms and techniques to analyze medical data. In recent years, liver disorders have excessively increased and liver diseases are becoming one...

Full description

Bibliographic Details
Main Authors: Bahramirad, Sina, Mustapha, Aida, Eshraghi, Maryam
Format: Conference or Workshop Item
Published: IEEE (IEEEXplore) 2013
Online Access:http://psasir.upm.edu.my/id/eprint/41298/
_version_ 1848849658383695872
author Bahramirad, Sina
Mustapha, Aida
Eshraghi, Maryam
author_facet Bahramirad, Sina
Mustapha, Aida
Eshraghi, Maryam
author_sort Bahramirad, Sina
building UPM Institutional Repository
collection Online Access
description Medical Data Mining (MDM) is one of the most critical aspects of automated disease diagnosis and disease prediction. MDM involves developing data mining algorithms and techniques to analyze medical data. In recent years, liver disorders have excessively increased and liver diseases are becoming one of the most fatal diseases in several countries. In this study, two real liver patient datasets were investigated for building classification models in order to predict liver diagnosis. Eleven data mining classification algorithms were applied to the datasets and the performance of all classifiers are compared against each other in terms of accuracy, precision, and recall. Several investigations have also been carried out to improve performance of the classification models. Finally, the results shown promising methodology in diagnosing liver disease during the earlier stages.
first_indexed 2025-11-15T09:53:54Z
format Conference or Workshop Item
id upm-41298
institution Universiti Putra Malaysia
institution_category Local University
last_indexed 2025-11-15T09:53:54Z
publishDate 2013
publisher IEEE (IEEEXplore)
recordtype eprints
repository_type Digital Repository
spelling upm-412982015-11-03T03:19:49Z http://psasir.upm.edu.my/id/eprint/41298/ Classification of liver disease diagnosis: a comparative study Bahramirad, Sina Mustapha, Aida Eshraghi, Maryam Medical Data Mining (MDM) is one of the most critical aspects of automated disease diagnosis and disease prediction. MDM involves developing data mining algorithms and techniques to analyze medical data. In recent years, liver disorders have excessively increased and liver diseases are becoming one of the most fatal diseases in several countries. In this study, two real liver patient datasets were investigated for building classification models in order to predict liver diagnosis. Eleven data mining classification algorithms were applied to the datasets and the performance of all classifiers are compared against each other in terms of accuracy, precision, and recall. Several investigations have also been carried out to improve performance of the classification models. Finally, the results shown promising methodology in diagnosing liver disease during the earlier stages. IEEE (IEEEXplore) 2013 Conference or Workshop Item NonPeerReviewed Bahramirad, Sina and Mustapha, Aida and Eshraghi, Maryam (2013) Classification of liver disease diagnosis: a comparative study. In: 2013 Second International Conference on Informatics and Applications (ICIA), 23-25 Sept. 2013, Poland. (pp. 42-46). 10.1109/ICoIA.2013.6650227
spellingShingle Bahramirad, Sina
Mustapha, Aida
Eshraghi, Maryam
Classification of liver disease diagnosis: a comparative study
title Classification of liver disease diagnosis: a comparative study
title_full Classification of liver disease diagnosis: a comparative study
title_fullStr Classification of liver disease diagnosis: a comparative study
title_full_unstemmed Classification of liver disease diagnosis: a comparative study
title_short Classification of liver disease diagnosis: a comparative study
title_sort classification of liver disease diagnosis: a comparative study
url http://psasir.upm.edu.my/id/eprint/41298/
http://psasir.upm.edu.my/id/eprint/41298/