Geometric Mean Maximum FSVMI Model and Its Application in Carotid Artery Stenosis Risk Prediction  

作　　者：ZHANG Xueying GUO Yuling LI Fenglian WEI Xin HU Fengyun HUI Haisheng JIA Wenhui 

机构地区：[1]College of Information and Computer,Taiyuan University of Technology,Jinzhong 030024,China [2]Department of Neurology,Shanxi Province People’s Hospital,Taiyuan 030012,China

出　　处：《Chinese Journal of Electronics》2021年第5期824-832,共9页电子学报（英文版）

基　　金：supported by the Key Research and Development Project of Shanxi Province,China(No.201803D31045,No.201603D321060);the Natural Science Foundation of Shanxi Province,China(No.201801D121138);the Project of Youth Fund of Shanxi Health Commission(No.201301029)。

摘　　要：Carotid artery stenosis is a serious medical condition that can lead to stroke.Using machine learning method to construct classifier model,carotid artery stenosis can be diagnosed with transcranial doppler data.We propose an improved fuzzy support vector machine model to predict carotid artery stenosis,with the maximum geometric mean as the optimization target.The fuzzy membership function is obtained by combining information entropy with the normalized class-center distance.Experimental results showed that the proposed model was superior to the benchmark models in sensitivity and geometric mean criteria.

关 键 词：Carotid artery stenosis risk prediction Imbalanced TCD dataset Fuzzy membership function Geometric mean maximum optimization target Fuzzy support vector machine with imbalanced regulator model 

分 类 号：R543.4[医药卫生—心血管疾病] TP181[医药卫生—内科学]