TY - GEN
T1 - ETD
T2 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
AU - Kim, Jungyoon
AU - Chu, Chao Hsien
PY - 2014/11/2
Y1 - 2014/11/2
N2 - Ventricular fibrillation (VF) is the most serious type of heart attack which requires quick detection and first aid to improve patients' survival rates. To be most effective in using wearable devices for VF detection, it is vital that the detection algorithms be accurate, robust, reliable and computationally efficient. Previous studies and our experiments both indicate that the time-delay (TD) algorithm has a high reliability for separating sinus rhythm (SR) from VF and is resistant to variable factors, such as window size and filtering method. However, it fails to detect some VF cases. In this paper, we propose an extended time-delay (ETD) algorithm for VF detection and conduct experiments comparing the performance of ETD against five good VF detection algorithms, including TD, using the popular Creighton University (CU) database. Our study shows that (1) TD and ETD outperform the other four algorithms considered and (2) with the same sensitivity setting, ETD improves upon TD in three other quality measures for up to 7.64% and in terms of aggregate accuracy, the ETD algorithm shows an improvement of 2.6% of the area under curve (AUC) compared to TD.
AB - Ventricular fibrillation (VF) is the most serious type of heart attack which requires quick detection and first aid to improve patients' survival rates. To be most effective in using wearable devices for VF detection, it is vital that the detection algorithms be accurate, robust, reliable and computationally efficient. Previous studies and our experiments both indicate that the time-delay (TD) algorithm has a high reliability for separating sinus rhythm (SR) from VF and is resistant to variable factors, such as window size and filtering method. However, it fails to detect some VF cases. In this paper, we propose an extended time-delay (ETD) algorithm for VF detection and conduct experiments comparing the performance of ETD against five good VF detection algorithms, including TD, using the popular Creighton University (CU) database. Our study shows that (1) TD and ETD outperform the other four algorithms considered and (2) with the same sensitivity setting, ETD improves upon TD in three other quality measures for up to 7.64% and in terms of aggregate accuracy, the ETD algorithm shows an improvement of 2.6% of the area under curve (AUC) compared to TD.
UR - http://www.scopus.com/inward/record.url?scp=84929501185&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84929501185&partnerID=8YFLogxK
U2 - 10.1109/EMBC.2014.6945112
DO - 10.1109/EMBC.2014.6945112
M3 - Conference contribution
C2 - 25571480
AN - SCOPUS:84929501185
T3 - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
SP - 6479
EP - 6482
BT - 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2014
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 26 August 2014 through 30 August 2014
ER -