Detection of Bundle Branch Blocks using Machine Learning Techniques

The most effective method used for the diagnosis of heart diseases is Electrocardiogram (ECG). shape ECG signal and time interval between its various components gives useful details about any underlying disease. Any dysfunction called as cardiac arrhythmia. electrical impulses are blocked due to arrhythmia Bundle Branch Block (BBB) which can be observed an irregular wave. BBB beats indicate serious precise quick detection arrhythmias from save lives also reduce diagnostics cost. This study presents a machine learning technique automatic BBB. In this both morphological statistical features were calculated signals available in standard MIT BIH database classify them normal, Left (LBBB) Right (RBBB). records MIT- containing Normal sinus rhythm, RBBB, LBBB study. suitability extracted was evaluated using three classifiers, support vector machine, k-nearest neighbours linear discriminant analysis. accuracy highly promising all classifiers with giving highest 98.2%. Since waveforms patients same disorder similar shape, proposed subject independent. thus reliable simple involving less computational complexity bundle branch block. system effort cardiologists thereby enabling concentrate more on treatment patients.