Development of a Computer-Aided Application for Analyzing ECG Signals and Detection of Cardiac Arrhythmia Using Back Propagation Neural Network - Part II: GUI Development

Electrocardiogram (ECG) is a graphic recording of the electrical activity produced by the heart.We have developed a computer-aided application model for classification of ECG signals for detection of cardiac arrhythmia.The model is based on some existing algorithms in literature which were adapted to suit our application.The developed model involves ECG signal pre-processing, extraction of some morphological features and simulating it with a trained Back Propagation Neural Network (BPNN) object.The application model has been investigated using the database of Massachusetts Institute of Technology Division of Health Science and Technology/Beth Israel Hospital (MIT-BIH).In this paper, in order to make the application (a software tool) user friendly, we present the development of a MATLAB based graphical user interface (GUI) for the application, which then makes it serve fully as a cost-effective computer aided application to analyze ECG signals for detection of cardiac arrhythmia.The performance of the developed application was investigated using the MIT-BIH database.Accuracy of 88.6%, sensitivity of 90%, specificity of 86.6%, and positive predictivity of 90% (based only on the MIT-BIH database used) shows that the developed application can be employed for the detection of heart diseases in patients.Also, the application is easy to use, fast, and gives the result of diagnosis as 'Normal' or 'Abnormal'.