×
Home Current Archive Editorial board
Instructions for papers
For Authors Aim & Scope Contact
Original scientific article

AN EARLY DETECTION OF KAWASAKI DISEASE USING ENHANCED FEATURE SELECTION AND HYBRIDIZATION-BASED CLASSIFICATION APPROACH

By
C. Kavitha Orcid logo ,
C. Kavitha

Mother Teresa Women’s University , Dindigul , India

A. Subramani Orcid logo
A. Subramani

M.V. Muthiah Govt. Arts College for Women , Dindigul , India

Abstract

Kawasaki disease (KD) is a disease that cause inflammation in blood vessels, impacting kids and causes heart and blood vessel damage. Patients with KD who have medium or big aneurysms, developing coronary dilatation for a minimum of 2 months, are related to the worst late coronary results, which are not widely researched. The primary goal of the suggested technique is to introduce an intelligent framework that can perform clinical data mining more accurately. In this, clinical data mining is done by using the novel hybridized classification approach. Initially, to replace the missing data, the Random Forest (RF) algorithm is proposed. Then, using the optimization algorithm, the feature selection is done, namely the artificial bee colony approach, which would select the best feature from the training data set. F-score values are considered as the fitness values for optimal feature selection. Finally, the classification process is done using the proposed hybridization approach; clustering is done before classification and in every iteration of classification. The clustering is done using the FCM clustering, and Deep neural network is employed for classification. The simulation results identified that the proposed hybridization approach has better classification accuracy, leading to an efficient assessment of KD.

References

1.
Makino N, Nakamura Y, Yashiro M, Kosami K, Matsubara Y, Ae R. Nationwide epidemiologic survey of Kawasaki disease in Japan,2015-2016. Pediatrics International. 2019;61(4):397–403.
2.
Kato H. Cardiovascular complications in Kawasaki disease: coronary artery lumen and long-term consequences. Progress in Pediatric Cardiology. 2004 Dec 1;19(2):137–45.
3.
Benseler SM, McCrindle BW, Silverman ED, Tyrrell PN, Wong J, Yeung RS. Infections and Kawasaki disease: implications for coronary artery outcome. Pediatrics. Dec 1;116(6):e760-6.
4.
Honkanen VE, McCrindle BW, Laxer RM, Feldman BM, Schneider R, Silverman ED. Clinical relevance of the risk factors for coronary artery inflammation in Kawasaki disease. Pediatric cardiology. 2003 Mar;24(2):122–6.
5.
Cimaz R, Sundel R. Atypical and incomplete Kawasaki disease. Best Practice & Research Clinical Rheumatology. 2009 Oct 1;23(5):689–97.

Citation

This is an open access article distributed under the  Creative Commons Attribution Non-Commercial License (CC BY-NC) License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. 

Article metrics

Google scholar: See link

The statements, opinions and data contained in the journal are solely those of the individual authors and contributors and not of the publisher and the editor(s). We stay neutral with regard to jurisdictional claims in published maps and institutional affiliations.