Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation

P. Langley; J. Allen; E. J. Bowers; M. J. Drinnan; E. V. Garcia; S. T. King; T. Olbrich; A. J. Sims; F. E. Smith; J. Wild; D. Zheng; A. Murray

doi:10.1109/CIC.2004.1443019

Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation

P. Langley, J. Allen, E. J. Bowers, M. J. Drinnan, E. V. Garcia, S. T. King, T. Olbrich, A. J. Sims, F. E. Smith, J. Wild, D. Zheng, A. Murray

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We assessed characteristics of atrial and ventricular activity from the ECG for predicting the oflset of atrial fibrillation for the 2004 PhysioNet/Computers in Cardiology Challenge. Seven parameters were analysed with five based on the statistical characteristics of the RR interval (mean, standard deviation, skewness, kurtosis and median beat-to-beat change), and fibrillation frequency and atrial signal amplitude. The power of the parameters to predict termination of the arrhythmia was assessed individually and in combination using linear discriminant analysis ( D A ) and a?t$cial neural network (ANN) techniques. Fibrillation fiequency with a threshold value of 5.55 Hz was able to idenrify 10/10 learning set records which terminated immediately (T) and 8/10 of non-terminating records (N) and was the best of the individual parameters. Classifcations for the test set for event 1 of the challenge for algorithms based on fibrillation frequency alone, LDA and ANN received scores of 24/30, 18/30 and 23/30 respectively. Low jibrillation frequency is an indicator of spontaneous termination of atrial fibrillation.

Original language	English
Title of host publication	Computers in Cardiology 2004
Publisher	IEEE
Pages	637-640
Number of pages	4
Volume	31
ISBN (Print)	0780389271
DOIs	https://doi.org/10.1109/CIC.2004.1443019
Publication status	Published - 22 Sept 2004
Externally published	Yes
Event	Computers in Cardiology 2004 - Chicago, United States Duration: 19 Sept 2004 → 22 Sept 2004

Conference

Conference	Computers in Cardiology 2004
Country/Territory	United States
City	Chicago
Period	19/09/04 → 22/09/04

Access to Document

10.1109/CIC.2004.1443019Licence: Unspecified

Cite this

Langley, P., Allen, J., Bowers, E. J., Drinnan, M. J., Garcia, E. V., King, S. T., Olbrich, T., Sims, A. J., Smith, F. E., Wild, J., Zheng, D., & Murray, A. (2004). Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation. In Computers in Cardiology 2004 (Vol. 31, pp. 637-640). IEEE. https://doi.org/10.1109/CIC.2004.1443019

@inproceedings{8fc246ae8f2949fda0171f6aec0a07ed,

title = "Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation",

abstract = "We assessed characteristics of atrial and ventricular activity from the ECG for predicting the oflset of atrial fibrillation for the 2004 PhysioNet/Computers in Cardiology Challenge. Seven parameters were analysed with five based on the statistical characteristics of the RR interval (mean, standard deviation, skewness, kurtosis and median beat-to-beat change), and fibrillation frequency and atrial signal amplitude. The power of the parameters to predict termination of the arrhythmia was assessed individually and in combination using linear discriminant analysis ( D A ) and a?t\$cial neural network (ANN) techniques. Fibrillation fiequency with a threshold value of 5.55 Hz was able to idenrify 10/10 learning set records which terminated immediately (T) and 8/10 of non-terminating records (N) and was the best of the individual parameters. Classifcations for the test set for event 1 of the challenge for algorithms based on fibrillation frequency alone, LDA and ANN received scores of 24/30, 18/30 and 23/30 respectively. Low jibrillation frequency is an indicator of spontaneous termination of atrial fibrillation. ",

author = "P. Langley and J. Allen and Bowers, \{E. J.\} and Drinnan, \{M. J.\} and Garcia, \{E. V.\} and King, \{S. T.\} and T. Olbrich and Sims, \{A. J.\} and Smith, \{F. E.\} and J. Wild and D. Zheng and A. Murray",

year = "2004",

month = sep,

day = "22",

doi = "10.1109/CIC.2004.1443019",

language = "English",

isbn = "0780389271",

volume = "31",

pages = "637--640",

booktitle = "Computers in Cardiology 2004",

publisher = "IEEE",

note = "Computers in Cardiology 2004 ; Conference date: 19-09-2004 Through 22-09-2004",

}

Langley, P, Allen, J, Bowers, EJ, Drinnan, MJ, Garcia, EV, King, ST, Olbrich, T, Sims, AJ, Smith, FE, Wild, J, Zheng, D & Murray, A 2004, Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation. in Computers in Cardiology 2004. vol. 31, IEEE, pp. 637-640, Computers in Cardiology 2004, Chicago, Illinois, United States, 19/09/04. https://doi.org/10.1109/CIC.2004.1443019

TY - GEN

T1 - Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation

AU - Langley, P.

AU - Allen, J.

AU - Bowers, E. J.

AU - Drinnan, M. J.

AU - Garcia, E. V.

AU - King, S. T.

AU - Olbrich, T.

AU - Sims, A. J.

AU - Smith, F. E.

AU - Wild, J.

AU - Zheng, D.

AU - Murray, A.

PY - 2004/9/22

Y1 - 2004/9/22

N2 - We assessed characteristics of atrial and ventricular activity from the ECG for predicting the oflset of atrial fibrillation for the 2004 PhysioNet/Computers in Cardiology Challenge. Seven parameters were analysed with five based on the statistical characteristics of the RR interval (mean, standard deviation, skewness, kurtosis and median beat-to-beat change), and fibrillation frequency and atrial signal amplitude. The power of the parameters to predict termination of the arrhythmia was assessed individually and in combination using linear discriminant analysis ( D A ) and a?t$cial neural network (ANN) techniques. Fibrillation fiequency with a threshold value of 5.55 Hz was able to idenrify 10/10 learning set records which terminated immediately (T) and 8/10 of non-terminating records (N) and was the best of the individual parameters. Classifcations for the test set for event 1 of the challenge for algorithms based on fibrillation frequency alone, LDA and ANN received scores of 24/30, 18/30 and 23/30 respectively. Low jibrillation frequency is an indicator of spontaneous termination of atrial fibrillation.

AB - We assessed characteristics of atrial and ventricular activity from the ECG for predicting the oflset of atrial fibrillation for the 2004 PhysioNet/Computers in Cardiology Challenge. Seven parameters were analysed with five based on the statistical characteristics of the RR interval (mean, standard deviation, skewness, kurtosis and median beat-to-beat change), and fibrillation frequency and atrial signal amplitude. The power of the parameters to predict termination of the arrhythmia was assessed individually and in combination using linear discriminant analysis ( D A ) and a?t$cial neural network (ANN) techniques. Fibrillation fiequency with a threshold value of 5.55 Hz was able to idenrify 10/10 learning set records which terminated immediately (T) and 8/10 of non-terminating records (N) and was the best of the individual parameters. Classifcations for the test set for event 1 of the challenge for algorithms based on fibrillation frequency alone, LDA and ANN received scores of 24/30, 18/30 and 23/30 respectively. Low jibrillation frequency is an indicator of spontaneous termination of atrial fibrillation.

UR - https://www.scopus.com/inward/citedby.url?scp=28244476908&partnerID=8YFLogxK

U2 - 10.1109/CIC.2004.1443019

DO - 10.1109/CIC.2004.1443019

M3 - Conference contribution

SN - 0780389271

VL - 31

SP - 637

EP - 640

BT - Computers in Cardiology 2004

PB - IEEE

T2 - Computers in Cardiology 2004

Y2 - 19 September 2004 through 22 September 2004

ER -

Analysis of RR interval and fibrillation frequency and amplitude for predicting spontaneous termination of atrial fibrillation

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this