An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification

Julio Cabanillas, Gustavo Tello, Brandon Mercado, Guillermo Kemper, Mirko Zimic, Robert Gilman

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

Abstract

The present work proposes an algorithm to calculate the QRS Score and the determination of confounders starting from Electrocardiographic (ECG) signals. The QRS Score is a parameter that indicates how big the scar is in the wall of the patient’s myocardium; It is also helpful in determining how healthy the heart is. Said parameter is calculated from signal information such as time measurements, amplitude relationships and waveforms. The evaluation of the ECG signals is usually done by visual perception of the graph paper where it is printed as a result of the electrocardiogram examination. However, the reproducibility of this method is 60% and the repeatability is 66%. This definitely affects the accuracy of the score obtained and therefore the diagnosis of a disease. The proposed algorithm aims to reduce the subjectivity of the analysis and standardize the punctuations to be obtained. The algorithm is made up of processing stages that involve the conditioning of the signal using finite impulse response (FIR) filters, decontamination of confounders by neural networks, detection of the QRS complex, detection of times and amplitudes and finally obtaining the QRS score from a table of criteria. Finally, the proposed algorithm obtained a reproducibility of 75% and a repeatability of 100% exceeding the performance of the specialist.

Original languageEnglish (US)
Title of host publicationProceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology
EditorsOsamu Saotome, Rangel Arthur, Vânia Vieira Estrela, Yuzo Iano, Hermes José Loschi
PublisherSpringer Science and Business Media Deutschland GmbH
Pages201-211
Number of pages11
ISBN (Print)9783030160524
DOIs
StatePublished - Jan 1 2019
Event4th Brazilian Technology Symposium, BTSym 2018 - Campinas, Brazil
Duration: Oct 23 2018Oct 25 2018

Publication series

NameSmart Innovation, Systems and Technologies
Volume140
ISSN (Print)2190-3018
ISSN (Electronic)2190-3026

Conference

Conference4th Brazilian Technology Symposium, BTSym 2018
CountryBrazil
CityCampinas
Period10/23/1810/25/18

Fingerprint

Neural networks
Decontamination
FIR filters
Time measurement
Electrocardiography
Processing
Evaluation
Impulse response
Conditioning
Filter
Subjectivity
Graph
Visual perception

Keywords

  • Chagas
  • Confounder
  • ECG signals
  • Neural networks
  • QRS score
  • Signal processing
  • Waveforms

ASJC Scopus subject areas

  • Decision Sciences(all)
  • Computer Science(all)

Cite this

Cabanillas, J., Tello, G., Mercado, B., Kemper, G., Zimic, M., & Gilman, R. (2019). An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification. In O. Saotome, R. Arthur, V. Vieira Estrela, Y. Iano, & H. J. Loschi (Eds.), Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology (pp. 201-211). (Smart Innovation, Systems and Technologies; Vol. 140). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-030-16053-1_19

An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification. / Cabanillas, Julio; Tello, Gustavo; Mercado, Brandon; Kemper, Guillermo; Zimic, Mirko; Gilman, Robert.

Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology. ed. / Osamu Saotome; Rangel Arthur; Vânia Vieira Estrela; Yuzo Iano; Hermes José Loschi. Springer Science and Business Media Deutschland GmbH, 2019. p. 201-211 (Smart Innovation, Systems and Technologies; Vol. 140).

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

Cabanillas, J, Tello, G, Mercado, B, Kemper, G, Zimic, M & Gilman, R 2019, An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification. in O Saotome, R Arthur, V Vieira Estrela, Y Iano & HJ Loschi (eds), Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology. Smart Innovation, Systems and Technologies, vol. 140, Springer Science and Business Media Deutschland GmbH, pp. 201-211, 4th Brazilian Technology Symposium, BTSym 2018, Campinas, Brazil, 10/23/18. https://doi.org/10.1007/978-3-030-16053-1_19
Cabanillas J, Tello G, Mercado B, Kemper G, Zimic M, Gilman R. An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification. In Saotome O, Arthur R, Vieira Estrela V, Iano Y, Loschi HJ, editors, Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology. Springer Science and Business Media Deutschland GmbH. 2019. p. 201-211. (Smart Innovation, Systems and Technologies). https://doi.org/10.1007/978-3-030-16053-1_19
Cabanillas, Julio ; Tello, Gustavo ; Mercado, Brandon ; Kemper, Guillermo ; Zimic, Mirko ; Gilman, Robert. / An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification. Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology. editor / Osamu Saotome ; Rangel Arthur ; Vânia Vieira Estrela ; Yuzo Iano ; Hermes José Loschi. Springer Science and Business Media Deutschland GmbH, 2019. pp. 201-211 (Smart Innovation, Systems and Technologies).
@inproceedings{364a92e2cb89450cb3e9d7c059a60461,
title = "An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification",
abstract = "The present work proposes an algorithm to calculate the QRS Score and the determination of confounders starting from Electrocardiographic (ECG) signals. The QRS Score is a parameter that indicates how big the scar is in the wall of the patient’s myocardium; It is also helpful in determining how healthy the heart is. Said parameter is calculated from signal information such as time measurements, amplitude relationships and waveforms. The evaluation of the ECG signals is usually done by visual perception of the graph paper where it is printed as a result of the electrocardiogram examination. However, the reproducibility of this method is 60{\%} and the repeatability is 66{\%}. This definitely affects the accuracy of the score obtained and therefore the diagnosis of a disease. The proposed algorithm aims to reduce the subjectivity of the analysis and standardize the punctuations to be obtained. The algorithm is made up of processing stages that involve the conditioning of the signal using finite impulse response (FIR) filters, decontamination of confounders by neural networks, detection of the QRS complex, detection of times and amplitudes and finally obtaining the QRS score from a table of criteria. Finally, the proposed algorithm obtained a reproducibility of 75{\%} and a repeatability of 100{\%} exceeding the performance of the specialist.",
keywords = "Chagas, Confounder, ECG signals, Neural networks, QRS score, Signal processing, Waveforms",
author = "Julio Cabanillas and Gustavo Tello and Brandon Mercado and Guillermo Kemper and Mirko Zimic and Robert Gilman",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/978-3-030-16053-1_19",
language = "English (US)",
isbn = "9783030160524",
series = "Smart Innovation, Systems and Technologies",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "201--211",
editor = "Osamu Saotome and Rangel Arthur and {Vieira Estrela}, V{\^a}nia and Yuzo Iano and Loschi, {Hermes Jos{\'e}}",
booktitle = "Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology",
address = "Germany",

}

TY - GEN

T1 - An algorithm to obtain the QRS score based on ECG parameters detection and neural networks for confounder classification

AU - Cabanillas, Julio

AU - Tello, Gustavo

AU - Mercado, Brandon

AU - Kemper, Guillermo

AU - Zimic, Mirko

AU - Gilman, Robert

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The present work proposes an algorithm to calculate the QRS Score and the determination of confounders starting from Electrocardiographic (ECG) signals. The QRS Score is a parameter that indicates how big the scar is in the wall of the patient’s myocardium; It is also helpful in determining how healthy the heart is. Said parameter is calculated from signal information such as time measurements, amplitude relationships and waveforms. The evaluation of the ECG signals is usually done by visual perception of the graph paper where it is printed as a result of the electrocardiogram examination. However, the reproducibility of this method is 60% and the repeatability is 66%. This definitely affects the accuracy of the score obtained and therefore the diagnosis of a disease. The proposed algorithm aims to reduce the subjectivity of the analysis and standardize the punctuations to be obtained. The algorithm is made up of processing stages that involve the conditioning of the signal using finite impulse response (FIR) filters, decontamination of confounders by neural networks, detection of the QRS complex, detection of times and amplitudes and finally obtaining the QRS score from a table of criteria. Finally, the proposed algorithm obtained a reproducibility of 75% and a repeatability of 100% exceeding the performance of the specialist.

AB - The present work proposes an algorithm to calculate the QRS Score and the determination of confounders starting from Electrocardiographic (ECG) signals. The QRS Score is a parameter that indicates how big the scar is in the wall of the patient’s myocardium; It is also helpful in determining how healthy the heart is. Said parameter is calculated from signal information such as time measurements, amplitude relationships and waveforms. The evaluation of the ECG signals is usually done by visual perception of the graph paper where it is printed as a result of the electrocardiogram examination. However, the reproducibility of this method is 60% and the repeatability is 66%. This definitely affects the accuracy of the score obtained and therefore the diagnosis of a disease. The proposed algorithm aims to reduce the subjectivity of the analysis and standardize the punctuations to be obtained. The algorithm is made up of processing stages that involve the conditioning of the signal using finite impulse response (FIR) filters, decontamination of confounders by neural networks, detection of the QRS complex, detection of times and amplitudes and finally obtaining the QRS score from a table of criteria. Finally, the proposed algorithm obtained a reproducibility of 75% and a repeatability of 100% exceeding the performance of the specialist.

KW - Chagas

KW - Confounder

KW - ECG signals

KW - Neural networks

KW - QRS score

KW - Signal processing

KW - Waveforms

UR - http://www.scopus.com/inward/record.url?scp=85068612521&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85068612521&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-16053-1_19

DO - 10.1007/978-3-030-16053-1_19

M3 - Conference contribution

AN - SCOPUS:85068612521

SN - 9783030160524

T3 - Smart Innovation, Systems and Technologies

SP - 201

EP - 211

BT - Proceedings of the 4th Brazilian Technology Symposium (BTSym’18) - Emerging Trends and Challenges in Technology

A2 - Saotome, Osamu

A2 - Arthur, Rangel

A2 - Vieira Estrela, Vânia

A2 - Iano, Yuzo

A2 - Loschi, Hermes José

PB - Springer Science and Business Media Deutschland GmbH

ER -