Premature atrial complexes detection using the Fisher Linear Discriminant

M Elgendi; Mirjam Jonkman; Friso De Boer

Premature atrial complexes detection using the Fisher Linear Discriminant

M Elgendi, Mirjam Jonkman, Friso De Boer

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

Abstract

Currently, no reliable method exists to detect Premature Atrial Complexes (PAC). The detection of PACs is clinically essential to predict supraventricular tachycardia, postoperative atrial fibrillation and paroxysmal atrial fibrillation. We propose an algorithm for intra-class classification that includes an analysis of the R-R time series. In the pre-processing phase, we used Butterworth filters to remove the baseline wander and the other noise. In the feature extraction phase, we detected the RR interval duration and the distance between the occurrence of P wave and T wave. Using these features we applied Fisher's Linear Discriminant to create a criterion that can be used for classification. Combining pre-processing, feature extraction and Fisher's Linear Discriminant we succeed in separating Normal and PAC beats with 99% Accuracy. � 2008 IEEE.

Original language	English
Title of host publication	Proceedings of the 7th IEEE International Conference on Cognitive Informatics ICCI 2008
Place of Publication	San Francisco, United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	-
Number of pages	6
Publication status	Published - 2008
Event	IEEE International Conference on Cognitive Informatics (ICCI) 2008 7th - Stanford, United States Duration: 14 Aug 2008 → 16 Aug 2008

Conference

Conference	IEEE International Conference on Cognitive Informatics (ICCI) 2008 7th
Period	14/08/08 → 16/08/08

Cite this

@inproceedings{de204681ddd44db5b83bd2d73a3425d7,

title = "Premature atrial complexes detection using the Fisher Linear Discriminant",

abstract = "Currently, no reliable method exists to detect Premature Atrial Complexes (PAC). The detection of PACs is clinically essential to predict supraventricular tachycardia, postoperative atrial fibrillation and paroxysmal atrial fibrillation. We propose an algorithm for intra-class classification that includes an analysis of the R-R time series. In the pre-processing phase, we used Butterworth filters to remove the baseline wander and the other noise. In the feature extraction phase, we detected the RR interval duration and the distance between the occurrence of P wave and T wave. Using these features we applied Fisher's Linear Discriminant to create a criterion that can be used for classification. Combining pre-processing, feature extraction and Fisher's Linear Discriminant we succeed in separating Normal and PAC beats with 99% Accuracy. � 2008 IEEE.",

keywords = "IIR filters, Time series analysis, Atrial fibrillations, Baseline wander, Butterworth filters, ECG arrhythmia detection, Fisher Linear discriminants, Fisher's Linear Discriminant, Fisher's linear discriminants, P waves, Paroxysmal atrial fibrillations, Pre-processing, Premature Atrial Complexes, Reliable methods, Rr intervals, Supraventricular tachycardias, T waves, Time series, Feature extraction",

author = "M Elgendi and Mirjam Jonkman and {De Boer}, Friso",

year = "2008",

language = "English",

pages = "--",

booktitle = "Proceedings of the 7th IEEE International Conference on Cognitive Informatics ICCI 2008",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "IEEE International Conference on Cognitive Informatics (ICCI) 2008 7th ; Conference date: 14-08-2008 Through 16-08-2008",

}

Elgendi, M, Jonkman, M & De Boer, F 2008, Premature atrial complexes detection using the Fisher Linear Discriminant. in Proceedings of the 7th IEEE International Conference on Cognitive Informatics ICCI 2008. IEEE, Institute of Electrical and Electronics Engineers, San Francisco, United States, pp. -, IEEE International Conference on Cognitive Informatics (ICCI) 2008 7th, 14/08/08.

Premature atrial complexes detection using the Fisher Linear Discriminant. / Elgendi, M; Jonkman, Mirjam ; De Boer, Friso.
Proceedings of the 7th IEEE International Conference on Cognitive Informatics ICCI 2008. San Francisco, United States: IEEE, Institute of Electrical and Electronics Engineers, 2008. p. -.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

TY - GEN

T1 - Premature atrial complexes detection using the Fisher Linear Discriminant

AU - Elgendi, M

AU - Jonkman, Mirjam

AU - De Boer, Friso

PY - 2008

Y1 - 2008

N2 - Currently, no reliable method exists to detect Premature Atrial Complexes (PAC). The detection of PACs is clinically essential to predict supraventricular tachycardia, postoperative atrial fibrillation and paroxysmal atrial fibrillation. We propose an algorithm for intra-class classification that includes an analysis of the R-R time series. In the pre-processing phase, we used Butterworth filters to remove the baseline wander and the other noise. In the feature extraction phase, we detected the RR interval duration and the distance between the occurrence of P wave and T wave. Using these features we applied Fisher's Linear Discriminant to create a criterion that can be used for classification. Combining pre-processing, feature extraction and Fisher's Linear Discriminant we succeed in separating Normal and PAC beats with 99% Accuracy. � 2008 IEEE.

AB - Currently, no reliable method exists to detect Premature Atrial Complexes (PAC). The detection of PACs is clinically essential to predict supraventricular tachycardia, postoperative atrial fibrillation and paroxysmal atrial fibrillation. We propose an algorithm for intra-class classification that includes an analysis of the R-R time series. In the pre-processing phase, we used Butterworth filters to remove the baseline wander and the other noise. In the feature extraction phase, we detected the RR interval duration and the distance between the occurrence of P wave and T wave. Using these features we applied Fisher's Linear Discriminant to create a criterion that can be used for classification. Combining pre-processing, feature extraction and Fisher's Linear Discriminant we succeed in separating Normal and PAC beats with 99% Accuracy. � 2008 IEEE.

KW - IIR filters

KW - Time series analysis

KW - Atrial fibrillations

KW - Baseline wander

KW - Butterworth filters

KW - ECG arrhythmia detection

KW - Fisher Linear discriminants

KW - Fisher's Linear Discriminant

KW - Fisher's linear discriminants

KW - P waves

KW - Paroxysmal atrial fibrillations

KW - Pre-processing

KW - Premature Atrial Complexes

KW - Reliable methods

KW - Rr intervals

KW - Supraventricular tachycardias

KW - T waves

KW - Time series

KW - Feature extraction

M3 - Conference Paper published in Proceedings

SP - -

BT - Proceedings of the 7th IEEE International Conference on Cognitive Informatics ICCI 2008

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - San Francisco, United States

T2 - IEEE International Conference on Cognitive Informatics (ICCI) 2008 7th

Y2 - 14 August 2008 through 16 August 2008

ER -

Premature atrial complexes detection using the Fisher Linear Discriminant

Abstract

Conference

Fingerprint

Cite this