Evaluation of electrocardiogram beat detection algorithms: patient specific versus generic training

T Last, CD Nugent, FJ Owens

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

The present study discusses two different training techniques for electrocardiogram (ECG) beat detection algorithms. The first technique is a patient specific training method which uses data from the patient's ECG signal to train the beat detector. The second technique is more generic as opposed to patient specific and uses ECG information from a database consisting of a number of patient records to train the detector. Four different beat detection algorithms were considered to facilitate the evaluation of the influence of the training techniques in relation to beat detection performance; a non-syntactic approach, a cross-correlation (CC) approach, a multi-component based CC technique and a multi-component based neural network (NN) technique. An ECG database containing approximately 3000 annotated beats was used for training and test. Superior results were attained with the patient specific training technique. The performance of the two multi-component based classifiers were increased by up to 22% for P-wave and T-wave detection for the patient specific training approach compared to the generic training approach.
LanguageEnglish
Title of host publicationUnknown Host Publication
Pages3208-3211
Number of pages4
DOIs
Publication statusPublished - Aug 2007
Event29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Lyon, France
Duration: 1 Aug 2007 → …

Conference

Conference29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
Period1/08/07 → …

Fingerprint

Electrocardiography
Detectors
Classifiers
Neural networks

Cite this

@inproceedings{11d8dcee63ef46b788b1da984cda5010,
title = "Evaluation of electrocardiogram beat detection algorithms: patient specific versus generic training",
abstract = "The present study discusses two different training techniques for electrocardiogram (ECG) beat detection algorithms. The first technique is a patient specific training method which uses data from the patient's ECG signal to train the beat detector. The second technique is more generic as opposed to patient specific and uses ECG information from a database consisting of a number of patient records to train the detector. Four different beat detection algorithms were considered to facilitate the evaluation of the influence of the training techniques in relation to beat detection performance; a non-syntactic approach, a cross-correlation (CC) approach, a multi-component based CC technique and a multi-component based neural network (NN) technique. An ECG database containing approximately 3000 annotated beats was used for training and test. Superior results were attained with the patient specific training technique. The performance of the two multi-component based classifiers were increased by up to 22{\%} for P-wave and T-wave detection for the patient specific training approach compared to the generic training approach.",
author = "T Last and CD Nugent and FJ Owens",
year = "2007",
month = "8",
doi = "10.1109/IEMBS.2007.4353012",
language = "English",
isbn = "1-4244-0788-5",
pages = "3208--3211",
booktitle = "Unknown Host Publication",

}

Last, T, Nugent, CD & Owens, FJ 2007, Evaluation of electrocardiogram beat detection algorithms: patient specific versus generic training. in Unknown Host Publication. pp. 3208-3211, 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 1/08/07. https://doi.org/10.1109/IEMBS.2007.4353012

Evaluation of electrocardiogram beat detection algorithms: patient specific versus generic training. / Last, T; Nugent, CD; Owens, FJ.

Unknown Host Publication. 2007. p. 3208-3211.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Evaluation of electrocardiogram beat detection algorithms: patient specific versus generic training

AU - Last, T

AU - Nugent, CD

AU - Owens, FJ

PY - 2007/8

Y1 - 2007/8

N2 - The present study discusses two different training techniques for electrocardiogram (ECG) beat detection algorithms. The first technique is a patient specific training method which uses data from the patient's ECG signal to train the beat detector. The second technique is more generic as opposed to patient specific and uses ECG information from a database consisting of a number of patient records to train the detector. Four different beat detection algorithms were considered to facilitate the evaluation of the influence of the training techniques in relation to beat detection performance; a non-syntactic approach, a cross-correlation (CC) approach, a multi-component based CC technique and a multi-component based neural network (NN) technique. An ECG database containing approximately 3000 annotated beats was used for training and test. Superior results were attained with the patient specific training technique. The performance of the two multi-component based classifiers were increased by up to 22% for P-wave and T-wave detection for the patient specific training approach compared to the generic training approach.

AB - The present study discusses two different training techniques for electrocardiogram (ECG) beat detection algorithms. The first technique is a patient specific training method which uses data from the patient's ECG signal to train the beat detector. The second technique is more generic as opposed to patient specific and uses ECG information from a database consisting of a number of patient records to train the detector. Four different beat detection algorithms were considered to facilitate the evaluation of the influence of the training techniques in relation to beat detection performance; a non-syntactic approach, a cross-correlation (CC) approach, a multi-component based CC technique and a multi-component based neural network (NN) technique. An ECG database containing approximately 3000 annotated beats was used for training and test. Superior results were attained with the patient specific training technique. The performance of the two multi-component based classifiers were increased by up to 22% for P-wave and T-wave detection for the patient specific training approach compared to the generic training approach.

UR - http://www.embc07.ulster.ac.uk/

UR - http://www.embc07.ulster.ac.uk/

U2 - 10.1109/IEMBS.2007.4353012

DO - 10.1109/IEMBS.2007.4353012

M3 - Conference contribution

SN - 1-4244-0788-5

SP - 3208

EP - 3211

BT - Unknown Host Publication

ER -