English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2318037      Online Users : 35
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/51194

Title: Prediction of coronary artery disease based on ensemble learning approaches and co-expressed observations
Authors: Ying-Tsang Lo
Hamido Fujita
Tun-Wen Pai
Contributors: 國立臺灣海洋大學:資訊工程學系
Keywords: Coronary artery disease (CAD)
ensemble learning
co-expressed observation
TOPSIS
Date: 2016-02
Issue Date: 2018-11-15T07:45:42Z
Publisher: Journal of Mechanics in Medicine and Biology
Abstract: Abstract: Background: Coronary artery disease (CAD) is one of the most representative cardiovascular diseases. Early and accurate prediction of CAD based on physiological measurements can reduce the risk of heart attack through medicine therapy, healthy diet, and regular physical activity. Methods:Four heart disease datasets from the UC Irvine Machine Learning Repository were combined and re-examined to remove incomplete entries, and a total of 822 cases were utilized in this study. Seven machine learning methods, including Naïve Bayes, artificial neural networks (ANNs), sequential minimal optimization (SMO), k-nearest neighbor (KNN), AdaBoost, J48, and random forest, were adopted to analyze the collected datasets for CAD prediction. By combining co-expressed observations and an ensemble voting mechanism, we designed and evaluated a new medical decision classifier for CAD prediction. The TOPSIS (Technique for Order Preference by Similarity to an Ideal Solution) algorithm was applied to determine the best prediction method for CAD diagnosis. Results: Features of systolic blood pressure, cholesterol, heart rate, and ST depression are considered to be the most significant differences between patients with and without CADs. We show that the prediction capability of seven machine learning classifiers can be enhanced by integrating combinations of observed co-expressed features. Finally, compared to the use of any single classifier, the proposed voting mechanism achieved optimal performance according to TOPSIS.
Relation: 16(1)
URI: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/51194
Appears in Collections:[資訊工程學系] 期刊論文

Files in This Item:

File Description SizeFormat
index.html0KbHTML6View/Open


All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback