The International Arab Journal of Information Technology (IAJIT)


Detection of Bundle Branch Block using Higher Order Statistics and Temporal Features

Yasin Kaya,
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.

[1] Allami R., Stranieri A., Jelinek H., and Balasubramanian V., “A Genetic Algorithm: Neural Network Wrapper Approach for Bundle Branch Block Detection,” in Proceedings of Computing in Cardiology Conference (CinC), Vancouver, pp. 461-464, 2016.

[2] Ashley E. and Niebauer J., Cardiology Explained, Remedica, 2004.

[3] Belkadi M. and Daamouche A., “Swarm Intelligence Approach to QRS Detection,” The International Arab Journal of Information Technology, vol. 17, no. 4, pp. 480-487, 2020.

[4] Bhattacharyya S. and Snekhalatha U., “Classification of Right Bundle Branch Block and Left Bundle Branch Block Cardiac Arrhythmias Based on ECG Analysis,” in Proceedings of Artificial Intelligence and Evolutionary Algorithms in Engineering Systems, Kumaracoil, pp. 331-341, 2015.

[5] Ceylan R. and Özbay Y., “Wavelet Neural Network for Classification of Bundle Branch Blocks,” in Proceedings of the World Congress on Engineering, London, pp. 1-5, 2011.

[6] Davydov N. and Khramov A., “Bundle branch Block Detection based on QRS Analysis of Digital ECG Signal,” Journal of Biomedical Photonics and Engineering, vol. 2, no. 3, pp. 030401, 2016.

[7] Fu K., Qu J., Chai Y., and Dong Y., “Classification of Seizure Based on The Time- Detection of Bundle Branch Block using Higher Order Statistics and Temporal Features 285 Frequency Image of EEG Signals Using HHT and SVM,” Biomedical Signal Processing and Control, vol. 13, pp. 15-22, 2014.

[8] Geiter H., “Understanding Bundle-Branch Blocks,” Nursing Critical Care, vol. 5, no. 6, pp. 5-8, 2010.

[9] Goeirmanto L., Mengko R., and Rajab T., “Comparison of The Calculation Qrs Angle for Bundle Branch Block Detection,” IOP Conference Series Materials Science and Engineering, vol. 128, no. 1, pp. 012037, 2016.

[10] Groeneveld R. and Meeden G., “Measuring Skewness and Kurtosis,” Journal of the Royal Statistical Society, vol. 33, no. 4, pp. 391-399, 1984.

[11] Hao C., Sivanesan S., Majmudar M., and Rajput K., “Combinational Feature Based Random Forest Classification for Enhanced Bundle Branch Block Beat Detection,” in Proceedings of IEEE EMBS International Conference on Biomedical and Health Informatics, Las Vegas, pp. 319-322, 2018.

[12] Hou B., Yang J., Wang P., and Yan R., “LSTM- Based Auto-Encoder Model for ECG Arrhythmias Classification,” IEEE Transactions on Instrumentation and Measurement, vol. 69, no. 4, pp. 1232-1240, 2020.

[13] Huang H., Liu J., Zhu Q., Wang R., and Hu G., “Detection of Inter-Patient Left and Right Bundle Branch Block Heartbeats in ECG Using Ensemble Classifiers,” BioMedical Engineering OnLine, vol. 13, pp. 72, 2014.

[14] Huang J., Chen B., Yao B., and He W., “ECG Arrhythmia Classification Using STFT-Based Spectrogram and Convolutional Neural Network,” IEEE Access, vol. 7, pp. 92871-92880, 2019.

[15] Isin A. and Ozdalili S., “Cardiac Arrhythmia Detection Using Deep Learning,” Procedia Computer Science, vol. 120, pp. 268-275, 2017.

[16] Kaya Y., Gürcan F., and Pehlivan H., “Genetic Feature Selection for Detection Bundle Branch Block Beats of ECG,” in Proceedings of 1nd International Turkish World Enginering and Science Congress, Antalya, pp. 87-95, 2017.

[17] Kaya Y. and Pehlivan H., “Feature Selection Using Genetic Algorithms for Premature Ventricular Contraction Classification,” in Proceedings of 9th International Conference on Electrical and Electronics Engineering, Bursa, pp. 1229-1232, 2015.

[18] Kaya Y. and Pehlivan H., “Classification of Premature Ventricular Contraction in ECG,” International Journal of Advanced Computer Science and Applications, vol. 6, no. 7, pp. 34- 40, 2015.

[19] Kaya Y., Pehlivan H., and Tenekeci M., “Effective ECG Beat Classification Using Higher Order Statistic Features and Genetic Feature Selection,” Biomedical Research, vol. 28, no. 17, pp. 7594-7603, 2017.

[20] Kora P. and Krishna K., “Hybrid Firefly and Particle Swarm Optimization Algorithm for the Detection of Bundle Branch Block,” International Journal of the Cardiovascular Academy, vol. 2, no. 1, pp. 44-48, 2016.

[21] Kora P. and Krishna K., “Bundle Block Detection Using Genetic Neural Network,” in Proceedings of Information Systems Design and Intelligent Applications, Visakhapatnam, pp. 309-317, 2016.

[22] Kora P. and Krishna K., “Detection of Bundle Branch Block Using Bat Algorithm and Levenberg Marquardt Neural Network,” in Proceedings of 1st International Conference on Information and Communication Technology for Intelligent Systems: Volume 1. Smart Innovation, Systems and Technologies, Ahmedabad, pp. 553- 561, 2016.

[23] Kora P. and Kalva S., “Detection of Bundle Branch Block using Adaptive Bacterial Foraging Optimization and Neural Network,” Egyptian Informatics Journal, vol. 18, no. 1, pp. 67-74, 2017.

[24] Moody G. and Mark R., “The Impact of the MIT- BIH Arrhythmia Database,” IEEE Engineering in Medicine and Biology Magazine, vol. 20, no. 3, pp. 45-50, 2001.

[25] Yang J. and Honavar V., “Feature Subset Selection Using A Genetic Algorithm,” IEEE Intelligent Systems and their Applications, vol. 13, no. 2, pp. 44-49, 1998.

[26] Yang, T., Gregg R., and Babaeizadeh S., “Detection of Strict Left Bundle Branch Block by Neural Network and A Method to Test Detection Consistency,” Physiological Measurement, vol. 41, no. 2, 2020. Yasin Kaya received the B.S. degree in Statistics and Computer Science in 1999 and his M.S. and Ph.D. degrees in Computer Engineering in 2006 and 2017, respectively, from the Karadeniz Technical University, Trabzon, Turkey. Since 2018 he has been an assistant professor at the Computer Engineering Department of Adana Alparslan Türkeş Science and Technology University, Turkey. He has published several journal and conference articles in his areas. His research interests include biomedical signal processing, arrhythmia detection and classification, biomedical image processing, pattern recognition, and nature inspired algorithms.