Home  /  Entropy  /  Vol: 19 Núm: 9 Par: Septemb (2017)  /  Article
ARTICLE
TITLE

Automated Diagnosis of Myocardial Infarction ECG Signals Using Sample Entropy in Flexible Analytic Wavelet Transform Framework

SUMMARY

Myocardial infarction (MI) is a silent condition that irreversibly damages the heart muscles. It expands rapidly and, if not treated timely, continues to damage the heart muscles. An electrocardiogram (ECG) is generally used by the clinicians to diagnose the MI patients. Manual identification of the changes introduced by MI is a time-consuming and tedious task, and there is also a possibility of misinterpretation of the changes in the ECG. Therefore, a method for automatic diagnosis of MI using ECG beat with flexible analytic wavelet transform (FAWT) method is proposed in this work. First, the segmentation of ECG signals into beats is performed. Then, FAWT is applied to each ECG beat, which decomposes them into subband signals. Sample entropy (SEnt) is computed from these subband signals and fed to the random forest (RF), J48 decision tree, back propagation neural network (BPNN), and least-squares support vector machine (LS-SVM) classifiers to choose the highest performing one. We have achieved highest classification accuracy of 99.31% using LS-SVM classifier. We have also incorporated Wilcoxon and Bhattacharya ranking methods and observed no improvement in the performance. The proposed automated method can be installed in the intensive care units (ICUs) of hospitals to aid the clinicians in confirming their diagnosis.

 Articles related

M. M. Ryhan    

This article discusses the possibility of establishing an information base for automated diagnosis and predicting the outcomes of surgery in gonarthrosis. The unified information document provides the creation of three-dimensional space for decision­maki... see more


T. A. Chernyshova, S. M. Zlepko, O. Yu. Azarkhov, S. O. Danylkov, V. Ye. Kryvonosov, D. M. Baranovsky    

Most modern systems and technologies of the automated analysis of medical microscopic images and early diagnostics of oncological diseases are analyzed in the article. The methods and algorithms used for image processing, segmentation, determination of p... see more


Max Roberto Batista Araújo,Luisa Ferreira Seabra,Mireille Ângela Bernardes Sousa    

Introduction: Identification of yeast species has clinical and epidemiological value. Different methods can be used, such as chromogenic media, microculture on corn meal agar with Tween 80, as well as conventional biochemical and automated methods. Recen... see more


Kunal Ostwal,Anne Wilkinson    

The  objective  of  the  study  was  to  determine  whether  the  information  of  combined  flagging  and  histogram recognition can be of aid in identifying cases of acute leuk ... see more


A. Anis,M. A. Fahiem,H. Tauseef    

Hypertension is known to be a major cause of death around the world. The death rate for this disease has increased up to 94% since last decade. Due to this disease, dangerous health conditions arise like heart failure, kidney failure and stroke. To preve... see more

Revista: The Nucleus