Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Chen, Xia | Jin, Wenquana | Wu, Qiruib; * | Zhang, Wenboa; * | Liang, Haimingc
Affiliations: [a] School of Economics & Management, Xidian University, Xi’an, China | [b] School of Foreign Languages, Xidian University, China | [c] Business School, Sichuan University, Chengdu, China
Correspondence: [*] Corresponding authors. Qirui Wu, School of Foreign Languages, Xidian University, Xi’an 710126, China. E-mail: qrwu@xidian.edu.cn and Wenbo Zhang, School of Economics & Management, Xidian University, Xi’an 710126, China. E-mail: wenbozhang@stu.xidian.edu.cn.
Abstract: Automatic risk classification of diseases is one of the most significant health problems in medical and healthcare domain. However, the related studies are relative scarce. In this paper, we design an intelligent diagnosis model based on optimal machine learning algorithms with rich clinical data. First, the disease risk classification problem based on machine learning is defined. Then, the K-means clustering algorithm is used to validate the class label of given data, thereby removing misclassified instances from the original dataset. Furthermore, naive Bayesian algorithm is applied to build the final classifier by using 10-fold cross-validation method. In addition, a novel class-specific attribute weighted approach is adopted to alleviate the conditional independence assumption of naive Bayes, which means we assign each disease attribute a specific weight for each class. Last but not least, a hybrid cost-sensitive disease risk classification model is formulated, and a practical example from the University of California Irvine (UCI) machine learning database is used to illustrate the potential of the proposed method. Experimental results demonstrate that the approach is competitive with the state-of-the-art classifiers.
Keywords: Disease diagnosis, hybrid cost-sensitive machine learning (HCML), K-means clustering, naive Bayes (NB), conditional independence assumption
DOI: 10.3233/JIFS-213486
Journal: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 3, pp. 3039-3050, 2022
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
sales@iospress.com
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
info@iospress.nl
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office info@iospress.nl
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
china@iospress.cn
For editorial issues, like the status of your submitted paper or proposals, write to editorial@iospress.nl
如果您在出版方面需要帮助或有任何建, 件至: editorial@iospress.nl