TY - GEN
T1 - A genetic algorithm-neural network wrapper approach for bundle branch block detection
AU - Allami, Ragheed
AU - Stranieri, Andrew
AU - Balasubramanian, Venki
AU - Jelinek, Herbert F.
N1 - Funding Information:
R.A. expresses his special thanks to the Ministry of Higher Education and Scientific Research and The University of Technology in Iraq for supporting this work.
Publisher Copyright:
© 2016 CCAL.
PY - 2016/3/1
Y1 - 2016/3/1
N2 - A Bundle Branch Block (BBB) is a delay or obstruction along electrical impulse pathways in the heart. The automated detection and classification of a BBB is important for prompt, accurate diagnosis and treatment of heart conditions, especially in accurate identification, of left BBB. This work proposes a new wrapper based hybrid approach for the detection of BBB that uses a Genetic Algorithm (GA) in combination with Artificial Neural Networks (ANN) to improve classification accuracy. Nineteen temporal features and three morphological features were extracted and normalized for each heartbeat from standard ECG recordings obtained from the MIT-BIH Arrhythmia database. The GA-ANN Hybrid resulted in improved sensitivity, specificity and accuracy (98%, 98% and 98% respectively) compared to the Principal Components Analysis (PCA)-ANN method (55%, 98% and 77% respectively) in the presence of noise. The GA-ANN Hybrid provides a better, more accurate identification for presence of BBB from ECG recordings leading to more timely diagnosis and treatment outcomes.
AB - A Bundle Branch Block (BBB) is a delay or obstruction along electrical impulse pathways in the heart. The automated detection and classification of a BBB is important for prompt, accurate diagnosis and treatment of heart conditions, especially in accurate identification, of left BBB. This work proposes a new wrapper based hybrid approach for the detection of BBB that uses a Genetic Algorithm (GA) in combination with Artificial Neural Networks (ANN) to improve classification accuracy. Nineteen temporal features and three morphological features were extracted and normalized for each heartbeat from standard ECG recordings obtained from the MIT-BIH Arrhythmia database. The GA-ANN Hybrid resulted in improved sensitivity, specificity and accuracy (98%, 98% and 98% respectively) compared to the Principal Components Analysis (PCA)-ANN method (55%, 98% and 77% respectively) in the presence of noise. The GA-ANN Hybrid provides a better, more accurate identification for presence of BBB from ECG recordings leading to more timely diagnosis and treatment outcomes.
UR - https://www.scopus.com/pages/publications/85016129108
M3 - Conference contribution
AN - SCOPUS:85016129108
T3 - Computing in Cardiology
SP - 461
EP - 464
BT - Computing in Cardiology Conference, CinC 2016
A2 - Murray, Alan
PB - IEEE Computer Society
T2 - 43rd Computing in Cardiology Conference, CinC 2016
Y2 - 11 September 2016 through 14 September 2016
ER -