Rule Extraction From Support Vector Machines Using Ensemble Learning Approach: An Application for Diagnosis of Diabetes

Author

Longfei Han ; SenLin Luo ; Jianmin Yu ; Limin Pan ; Songjing Chen

Author_Institution

Beijing Inst. of Technol., Beijing, China

Volume

19

Issue

2

fYear

2015

fDate

Mar-15

Firstpage

728

Lastpage

734

Abstract

Diabetes mellitus is a chronic disease and a worldwide public health challenge. It has been shown that 50-80% proportion of T2DM is undiagnosed. In this paper, support vector machines are utilized to screen diabetes, and an ensemble learning module is added, which turns the “black box” of SVM decisions into comprehensible and transparent rules, and it is also useful for solving imbalance problem. Results on China Health and Nutrition Survey data show that the proposed ensemble learning method generates rule sets with weighted average precision 94.2% and weighted average recall 93.9% for all classes. Furthermore, the hybrid system can provide a tool for diagnosis of diabetes, and it supports a second opinion for lay users.

Keywords

diseases; feature extraction; learning (artificial intelligence); medical diagnostic computing; patient diagnosis; support vector machines; SVM decisions; chronic disease; diabetes diagnosis application; diabetes mellitus; ensemble learning approach; rule extraction; support vector machines; weighted average precision; worldwide public health challenge; Accuracy; Data models; Decision trees; Diabetes; Predictive models; Radio frequency; Support vector machines; diagnosis of diabetes; ensemble learning; random forest (RF); rule extraction; support vector machines (SVMs);

fLanguage

English

Journal_Title

Biomedical and Health Informatics, IEEE Journal of

Publisher

ieee

ISSN

2168-2194

Type

jour

DOI

10.1109/JBHI.2014.2325615

Filename

6818375