Detection of Bundle Branch Block using Higher
Order Statistics and Temporal Features
Yasin Kaya
Department of Computer Engineering, Adana
Alparslan Türkeş Science and Technology University, Turkey
Abstract: Bundle Branch Block (BBB) beats are the
most common Electrocardiogram
(ECG) arrhythmias and can be indicators of significant heart disease. This
study aimed to provide an effective machine-learning method for the detection
of BBB beats. To this purpose, statistical and temporal features were
calculated and the more valuable ones searched using feature selection
algorithms. Forward search, backward elimination and genetic algorithms were
used for feature selection. Three different classifiers, K-Nearest Neighbors
(KNN), neural networks, and support vector machines, were used comparatively in
this study. Accuracy, specificity, and sensitivity performance metrics were
calculated in order to compare the results. Normal sinus rhythm (N),
Right Bundle Branch Block
(RBBB), and Left Bundle Branch Block (LBBB) ECG beat types were used in the
study. All beats containing these three beat types in the MIT-BIH arrhythmia
database were used in the experiments. All of the feature sets were obtained at
a promising classification accuracy for BBB classification. The KNN classifier
using backward elimination-selected features achieved the highest
classification accuracy results in the study with 99.82%. The results showed
the proposed approach to be successful in the detection of BBB beats.
Keywords: ECG, arrhythmia detection, bundle branch block, genetic algorithms,
neural networks, k-nearest neighbors, support vector machines, backward
elimination, forward selection.
Received
August 20, 2019; accepted October 5, 2020