A hybrid approach to medical decision support systems: Combining feature selection, fuzzy weighted pre-processing and AIRS
Küçük Resim Yok
Tarih
2007
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
ELSEVIER IRELAND LTD
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
This paper presents a hybrid approach based on feature selection, fuzzy weighted preprocessing and artificial immune recognition system (AIRS) to medical decision support systems. we have used the heart disease and hepatitis disease datasets taken from UCI machine learning database as medical dataset. Artificial immune recognition system has shown an effective performance on several problems such as machine learning benchmark problems and medical classification problems like breast cancer diabetes and liver disorders classification. The proposed approach consists of three stages. In the first stage, the dimensions of heart disease and hepatitis disease datasets are reduced to 9 from 13 and 19 in the feature selection (FS) sub-program by means of C4.5 decision tree algorithm (CBA program), respectively In the second stage, heart disease and hepatitis disease datasets are normalized in the range of [0,1] and are weighted via fuzzy weighted pre-processing. In the third stage, weighted input values obtained from fuzzy weighted pre-processing are classified using AIRS classifier system. The obtained classification accuracies of our system are 9239% and 81.82% using 50-50% training-test split for heart disease and hepatitis disease datasets, respectively with these results, the proposed method can be used in medical decision support systems. (c) 2007 Elsevier Ireland Ltd. All rights reserved.
Açıklama
Anahtar Kelimeler
AIRS, fuzzy weighted pre-processing, feature selection, heart disease, hepatitis disease, medical decision-making
Kaynak
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
WoS Q Değeri
Q2
Scopus Q Değeri
Q1
Cilt
88
Sayı
2