Telecardiology and Teletreatment System Design for Heart Failures Using Type-2 Fuzzy Clustering Neural Networks

Proper diagnosis of heart failures is critical, since the appropriate treatments arestrongly dependent upon the underlying cause. Furthermore, rapid diagnosis is alsocritical, since the effectiveness of some treatments depends upon rapid initiation. In thispaper, a new web-based telecardiology system has been proposed for diagnosis,consultation, and treatment. The aim of this implemented telecardiology system is tohelp to practitioner doctor, if clinic findings of patient misgive heart failures. This modelconsists of three subsystems. The first subsystem divides into recording andpreprocessing phase. Here, electrocardiography signal is recorded from emergencypatient and this recorded signal is preprocessed for detection of RR interval. Thesecond subsystem realizes classification of RR interval. In other words, this secondsubsystem is used to diagnosis heart failures. In this study, a combined classificationsystem has been designed using type-2 fuzzy c-means clustering (T2FCM) algorithmand neural networks. T2FCM was used to improve performance of neural networkswhich was obtained very high performance accuracy to classify RR intervals of ECGsignals. This proposed automated telecardiology and diagnostic system assists topractitioner doctor to diagnosis heart failures easily. Training and testing data for thisdiagnostic system include five ECG signal classes. The third subsystem is consultationand teletreatment between practitioner (or family) doctor and cardiologist worked inresearch hospital with prepared web page (www.telekardiyoloji.com). However,opportunity of signal’s evaluation is presented to practitioner and expert doctor withprepared interfaces. T2FCM is applied to the training data for the selection of bestsegments in the second subsystem. A new training set formed by these best segmentswas classified using the neural networks classifier which has well-knownbackpropagation algorithm and generalized delta rule learning. Correct classificationrate was found as 100% using proposed Type-2 Fuzzy Clustering Neural Networks(T2FCNN) method.