Data mining usage in emboli detection

Abstract

Asymptomatic circulating cerebral emboli, which are particles bigger than blood cells, can be detected by transcranial Doppler ultrasound. In certain conditions asymptomatic embolic signals (ES) appear to be markers of increased stroke risk. ES, reflected by an embolus, have usually larger amplitude than the signals from normal blood flow and show a transient characteristic. A number of methods to detect cerebral emboli have been studied in the literature. In this study, data mining techniques have been used in order to increase sensitivity and specificity of an embolic signal detection system. The classification results of different methods have been compared by using a data set including 100 ES, 100 speckle and 100 artifact. The ROC analysis results show that adaptive neuro fuzzy inference (ANFIS) system method appears to give better results. © 2007 IEEE. © 2008 Elsevier B.V., All rights reserved.