TY - JOUR
T1 - Atrial fibrillation analysis for real time patient monitoring
AU - Allami, Ragheed
AU - Stranieri, Andrew
AU - Marzbanrad, Faezeh
AU - Balasubramanian, Venki
AU - Jelinek, Herbert F.
N1 - Funding Information:
Ragheed Allami expresses his special thanks to the Ministry of Higher Education & Scientific Research and The University of Technology in Iraq for supporting this work. The authors would like to thank the expert cardiologist Dr Saheb Al-Daher for his valuable recommendations, classifying ECG segments and providing specialist knowledge.
Publisher Copyright:
© 2017 IEEE Computer Society. All rights reserved.
PY - 2017
Y1 - 2017
N2 - Atrial Fibrillation (AF) can lead to life-threatening conditions such as stroke and heart failure. The instant recognition of life-threatening cardiac arrhythmias based on a 3-lead ECG to record a Lead II configuration for a few seconds is a challenging problem of clinical significance. Five consecutive ECG beats that were identified by a cardiologist to characterise an AF episode and five consecutive heartbeat intervals representing an irregular RR intervals episode were analysed. The detection and analysis of P waves as the morphological features of AF was executed based on two template matching methods. An AF detector was developed by combining the correlation coefficients based on the template matching methods and the standard deviation of the RR intervals. The AF detector was then applied to classify 5 consecutive beats as AF or non-AF based on thresholding the calculated irregularity. The proposed algorithm was tested on the MIT-BIH Atrial Fibrillation and the Challenge 2017 databases. The proposed method resulted in an improved sensitivity, specificity and accuracy of 97.60%, 98.20% and 99% respectively compared to recent published methods. In addition, the proposed method is suitable for real-time patient monitoring as it is computationally simple and requires only a few seconds of ECG recording to detect an AF rhythm.
AB - Atrial Fibrillation (AF) can lead to life-threatening conditions such as stroke and heart failure. The instant recognition of life-threatening cardiac arrhythmias based on a 3-lead ECG to record a Lead II configuration for a few seconds is a challenging problem of clinical significance. Five consecutive ECG beats that were identified by a cardiologist to characterise an AF episode and five consecutive heartbeat intervals representing an irregular RR intervals episode were analysed. The detection and analysis of P waves as the morphological features of AF was executed based on two template matching methods. An AF detector was developed by combining the correlation coefficients based on the template matching methods and the standard deviation of the RR intervals. The AF detector was then applied to classify 5 consecutive beats as AF or non-AF based on thresholding the calculated irregularity. The proposed algorithm was tested on the MIT-BIH Atrial Fibrillation and the Challenge 2017 databases. The proposed method resulted in an improved sensitivity, specificity and accuracy of 97.60%, 98.20% and 99% respectively compared to recent published methods. In addition, the proposed method is suitable for real-time patient monitoring as it is computationally simple and requires only a few seconds of ECG recording to detect an AF rhythm.
UR - https://www.scopus.com/pages/publications/85045117544
U2 - 10.22489/CinC.2017.118-272
DO - 10.22489/CinC.2017.118-272
M3 - Conference article
AN - SCOPUS:85045117544
SN - 2325-8861
VL - 44
SP - 1
EP - 4
JO - Computing in Cardiology
JF - Computing in Cardiology
T2 - 44th Computing in Cardiology Conference, CinC 2017
Y2 - 24 September 2017 through 27 September 2017
ER -
