Computer algorithms for evaluating the quality of ECGs in real time

Henian Xia, Gabriel A. Garcia, Joseph C. McBride, Adam Sullivan, Thibaut De Bock, Jujhar Bains, Dale Wortham, Xiaopeng Zhao

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

26 Citations (Scopus)

Abstract

ECG, measuring body-surface electrical waves generated in the heart, is the golden standard for diagnosis of various cardiovascular diseases. The 2011 Physionet challenge visions mobile phones that can be used to collect and analyse ECG records. Such devices are particularly useful in underdeveloped regions, which have a large population size but lack adequate primary care capacity. Signals collected using mobile phones can be sent via mobile network to experienced doctors for further diagnosis. In response to Physionet 2011 challenge, we explore various time series techniques for their potentials in evaluating quality of an ECG, including time domain analysis, frequency domain analysis, joint time-frequency analysis, self correlation, cross correlation, and entropy analysis. Two algorithms are developed based on these techniques. The first algorithm consists of multi-stage tests. A record that passes all tests is regarded as of acceptable quality. In the second algorithm, results from various analyses are assembled into a matrix, which measures the regularity of the ECG. The quality of the ECG is then measured by the spectrum radius of the Matrix of Regularity. Since spectrum radius is continuous, the results can lead to continuous grades of ECGs. The algorithms are tested using training data from Physionet. Influences of various parameters are examined.

Original languageEnglish (US)
Title of host publicationComputing in Cardiology 2011, CinC 2011
Pages369-372
Number of pages4
Volume38
StatePublished - 2011
Externally publishedYes
EventComputing in Cardiology 2011, CinC 2011 - Hangzhou, China
Duration: Sep 18 2011Sep 21 2011

Other

OtherComputing in Cardiology 2011, CinC 2011
CountryChina
CityHangzhou
Period9/18/119/21/11

Fingerprint

Electrocardiography
Cell Phones
Mobile phones
Frequency domain analysis
Time domain analysis
Bioelectric potentials
Entropy
Population Density
Time series
Wireless networks
Primary Health Care
Cardiovascular Diseases
Joints
Equipment and Supplies

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Cardiology and Cardiovascular Medicine

Cite this

Xia, H., Garcia, G. A., McBride, J. C., Sullivan, A., De Bock, T., Bains, J., ... Zhao, X. (2011). Computer algorithms for evaluating the quality of ECGs in real time. In Computing in Cardiology 2011, CinC 2011 (Vol. 38, pp. 369-372). [6164579]

Computer algorithms for evaluating the quality of ECGs in real time. / Xia, Henian; Garcia, Gabriel A.; McBride, Joseph C.; Sullivan, Adam; De Bock, Thibaut; Bains, Jujhar; Wortham, Dale; Zhao, Xiaopeng.

Computing in Cardiology 2011, CinC 2011. Vol. 38 2011. p. 369-372 6164579.

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

Xia, H, Garcia, GA, McBride, JC, Sullivan, A, De Bock, T, Bains, J, Wortham, D & Zhao, X 2011, Computer algorithms for evaluating the quality of ECGs in real time. in Computing in Cardiology 2011, CinC 2011. vol. 38, 6164579, pp. 369-372, Computing in Cardiology 2011, CinC 2011, Hangzhou, China, 9/18/11.
Xia H, Garcia GA, McBride JC, Sullivan A, De Bock T, Bains J et al. Computer algorithms for evaluating the quality of ECGs in real time. In Computing in Cardiology 2011, CinC 2011. Vol. 38. 2011. p. 369-372. 6164579
Xia, Henian ; Garcia, Gabriel A. ; McBride, Joseph C. ; Sullivan, Adam ; De Bock, Thibaut ; Bains, Jujhar ; Wortham, Dale ; Zhao, Xiaopeng. / Computer algorithms for evaluating the quality of ECGs in real time. Computing in Cardiology 2011, CinC 2011. Vol. 38 2011. pp. 369-372
@inproceedings{9c0eeded677548f98d10e2e4441c1aa4,
title = "Computer algorithms for evaluating the quality of ECGs in real time",
abstract = "ECG, measuring body-surface electrical waves generated in the heart, is the golden standard for diagnosis of various cardiovascular diseases. The 2011 Physionet challenge visions mobile phones that can be used to collect and analyse ECG records. Such devices are particularly useful in underdeveloped regions, which have a large population size but lack adequate primary care capacity. Signals collected using mobile phones can be sent via mobile network to experienced doctors for further diagnosis. In response to Physionet 2011 challenge, we explore various time series techniques for their potentials in evaluating quality of an ECG, including time domain analysis, frequency domain analysis, joint time-frequency analysis, self correlation, cross correlation, and entropy analysis. Two algorithms are developed based on these techniques. The first algorithm consists of multi-stage tests. A record that passes all tests is regarded as of acceptable quality. In the second algorithm, results from various analyses are assembled into a matrix, which measures the regularity of the ECG. The quality of the ECG is then measured by the spectrum radius of the Matrix of Regularity. Since spectrum radius is continuous, the results can lead to continuous grades of ECGs. The algorithms are tested using training data from Physionet. Influences of various parameters are examined.",
author = "Henian Xia and Garcia, {Gabriel A.} and McBride, {Joseph C.} and Adam Sullivan and {De Bock}, Thibaut and Jujhar Bains and Dale Wortham and Xiaopeng Zhao",
year = "2011",
language = "English (US)",
isbn = "9781457706127",
volume = "38",
pages = "369--372",
booktitle = "Computing in Cardiology 2011, CinC 2011",

}

TY - GEN

T1 - Computer algorithms for evaluating the quality of ECGs in real time

AU - Xia, Henian

AU - Garcia, Gabriel A.

AU - McBride, Joseph C.

AU - Sullivan, Adam

AU - De Bock, Thibaut

AU - Bains, Jujhar

AU - Wortham, Dale

AU - Zhao, Xiaopeng

PY - 2011

Y1 - 2011

N2 - ECG, measuring body-surface electrical waves generated in the heart, is the golden standard for diagnosis of various cardiovascular diseases. The 2011 Physionet challenge visions mobile phones that can be used to collect and analyse ECG records. Such devices are particularly useful in underdeveloped regions, which have a large population size but lack adequate primary care capacity. Signals collected using mobile phones can be sent via mobile network to experienced doctors for further diagnosis. In response to Physionet 2011 challenge, we explore various time series techniques for their potentials in evaluating quality of an ECG, including time domain analysis, frequency domain analysis, joint time-frequency analysis, self correlation, cross correlation, and entropy analysis. Two algorithms are developed based on these techniques. The first algorithm consists of multi-stage tests. A record that passes all tests is regarded as of acceptable quality. In the second algorithm, results from various analyses are assembled into a matrix, which measures the regularity of the ECG. The quality of the ECG is then measured by the spectrum radius of the Matrix of Regularity. Since spectrum radius is continuous, the results can lead to continuous grades of ECGs. The algorithms are tested using training data from Physionet. Influences of various parameters are examined.

AB - ECG, measuring body-surface electrical waves generated in the heart, is the golden standard for diagnosis of various cardiovascular diseases. The 2011 Physionet challenge visions mobile phones that can be used to collect and analyse ECG records. Such devices are particularly useful in underdeveloped regions, which have a large population size but lack adequate primary care capacity. Signals collected using mobile phones can be sent via mobile network to experienced doctors for further diagnosis. In response to Physionet 2011 challenge, we explore various time series techniques for their potentials in evaluating quality of an ECG, including time domain analysis, frequency domain analysis, joint time-frequency analysis, self correlation, cross correlation, and entropy analysis. Two algorithms are developed based on these techniques. The first algorithm consists of multi-stage tests. A record that passes all tests is regarded as of acceptable quality. In the second algorithm, results from various analyses are assembled into a matrix, which measures the regularity of the ECG. The quality of the ECG is then measured by the spectrum radius of the Matrix of Regularity. Since spectrum radius is continuous, the results can lead to continuous grades of ECGs. The algorithms are tested using training data from Physionet. Influences of various parameters are examined.

UR - http://www.scopus.com/inward/record.url?scp=84860007177&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860007177&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9781457706127

VL - 38

SP - 369

EP - 372

BT - Computing in Cardiology 2011, CinC 2011

ER -