A Diagnostic Model for Identification of Myocardial Infarction from Electrocardiography Signals

Authors : Aykut DİKER, Zafer CÖMERT, Engin AVCI

Pages : 132-139

Doi:10.17678/beuscitech.344953

View : 44 | Download : 6

Publication Date : 2017-12-26

Article Type : Research Paper

Abstract :Electrocardiography insert ignore into journalissuearticles values(ECG); is a useful test used commonly to observe the electrical activity of a heart. Recently, a growing relationship has been observed between diagnosis of a disease and using of machine learning techniques. In this scope, a diagnostic application model designed based on a combination of Recursive Feature Eliminator insert ignore into journalissuearticles values(RFE); and two different machine learning algorithms called as -nearest neighbors insert ignore into journalissuearticles values( -NN); and artificial neural network insert ignore into journalissuearticles values(ANN); is proposed for classification of ECG signals in this study. The experiments performed on an open-access ECG database. Firstly, the signals were passed a pre-processing step. Then, several diagnostic features from morphological and statistical domains were extracted from the signals. In the last stage of the analysis, RFE algorithm covering 10-fold cross-validation and the mentioned machine learning techniques were employed to separate abnormal Myocardial Infarction insert ignore into journalissuearticles values(MI); samples from normal. The promising results as accuracy of 80.60%, sensitivity of 86.58% and specificity of 64.71% were achieved. The validation of the contribution was checked by comparing the performances of both -NN and ANN to related works. Consequently, the proposed diagnostic model ensured an automatic and robust ECG signal classification model.
Keywords : Biomedical Signal Processing, Decision Support System, Machine Learning, Electrocardiography

ORIGINAL ARTICLE URL