An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism

Kevin Picón; Juan Rodriguez; Rodrigo Salazar-Gamarra; Manuel Márquez; Guillermo Kemper

doi:10.1007/978-3-031-31007-2_15

An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism

Kevin Picón
, Juan Rodriguez
, Rodrigo Salazar-Gamarra
, Manuel Márquez
, Guillermo Kemper

Faculty of Engineering

Universidad Peruana de Ciencias Aplicadas

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

Abstract

This work proposes an algorithm to reconstruct 4 precordial electrocardiogram (ECG) lead signals. Standard cardiovascular disease (CVD) monitoring and detection uses all 12 available ECG leads. However, this number of leads implies a certain complexity of the equipment in terms of size, weight, and power consumption. Computational algorithms aimed at reducing the number of required leads for CVD detection help lower the time consumption and errors due to needing many signal acquisition cables. In this work, an LSTM sequence-to-sequence (Seq2Seq) neural network model with attention takes only 4 ECG leads (I, II, V2, and V5) and outputs the mentioned precordial leads. This proposal contributes to making ECG signal acquisitions easier and more accessible by requiring fewer cables and thus facilitating its use by people with little training. The model achieved a maximum average Pearson correlation coefficient of 0.9707 for all leads. It was validated using the PTB Diagnostic ECG Database.

Original language	English
Title of host publication	Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology
Editors	Yuzo Iano, Osamu Saotome, Guillermo Leopoldo Kemper Vásquez, Maria Thereza de Moraes Gomes Rosa, Rangel Arthur, Gabriel Gomes de Oliveira
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	154-163
Number of pages	10
ISBN (Print)	9783031310065
DOIs	https://doi.org/10.1007/978-3-031-31007-2_15
State	Published - 2023
Event	8th Brazilian Technology Symposium, BTSym 2022 - Virtual, online Duration: 24 Oct 2022 → 26 Oct 2022

Publication series

Name	Smart Innovation, Systems and Technologies
Volume	353 SIST
ISSN (Print)	2190-3018
ISSN (Electronic)	2190-3026

Conference

Conference	8th Brazilian Technology Symposium, BTSym 2022
City	Virtual, online
Period	24/10/22 → 26/10/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Attention mechanism
ECG leads
LSTM
Reconstruction

Access to Document

10.1007/978-3-031-31007-2_15

Cite this

Picón, K., Rodriguez, J., Salazar-Gamarra, R., Márquez, M., & Kemper, G. (2023). An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism. In Y. Iano, O. Saotome, G. L. Kemper Vásquez, M. T. de Moraes Gomes Rosa, R. Arthur, & G. Gomes de Oliveira (Eds.), Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology (pp. 154-163). (Smart Innovation, Systems and Technologies; Vol. 353 SIST). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-31007-2_15

Picón, Kevin ; Rodriguez, Juan ; Salazar-Gamarra, Rodrigo et al. / An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism. Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology. editor / Yuzo Iano ; Osamu Saotome ; Guillermo Leopoldo Kemper Vásquez ; Maria Thereza de Moraes Gomes Rosa ; Rangel Arthur ; Gabriel Gomes de Oliveira. Springer Science and Business Media Deutschland GmbH, 2023. pp. 154-163 (Smart Innovation, Systems and Technologies).

@inproceedings{f0b8a9c2d49349de9582737214f1d6c4,

title = "An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism",

abstract = "This work proposes an algorithm to reconstruct 4 precordial electrocardiogram (ECG) lead signals. Standard cardiovascular disease (CVD) monitoring and detection uses all 12 available ECG leads. However, this number of leads implies a certain complexity of the equipment in terms of size, weight, and power consumption. Computational algorithms aimed at reducing the number of required leads for CVD detection help lower the time consumption and errors due to needing many signal acquisition cables. In this work, an LSTM sequence-to-sequence (Seq2Seq) neural network model with attention takes only 4 ECG leads (I, II, V2, and V5) and outputs the mentioned precordial leads. This proposal contributes to making ECG signal acquisitions easier and more accessible by requiring fewer cables and thus facilitating its use by people with little training. The model achieved a maximum average Pearson correlation coefficient of 0.9707 for all leads. It was validated using the PTB Diagnostic ECG Database.",

keywords = "Attention mechanism, ECG leads, LSTM, Reconstruction",

author = "Kevin Pic{\'o}n and Juan Rodriguez and Rodrigo Salazar-Gamarra and Manuel M{\'a}rquez and Guillermo Kemper",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; 8th Brazilian Technology Symposium, BTSym 2022 ; Conference date: 24-10-2022 Through 26-10-2022",

year = "2023",

doi = "10.1007/978-3-031-31007-2\_15",

language = "Ingl{\'e}s",

isbn = "9783031310065",

series = "Smart Innovation, Systems and Technologies",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "154--163",

editor = "Yuzo Iano and Osamu Saotome and \{Kemper V{\'a}squez\}, \{Guillermo Leopoldo\} and \{de Moraes Gomes Rosa\}, \{Maria Thereza\} and Rangel Arthur and \{Gomes de Oliveira\}, Gabriel",

booktitle = "Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology",

}

Picón, K, Rodriguez, J, Salazar-Gamarra, R, Márquez, M & Kemper, G 2023, An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism. in Y Iano, O Saotome, GL Kemper Vásquez, MT de Moraes Gomes Rosa, R Arthur & G Gomes de Oliveira (eds), Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology. Smart Innovation, Systems and Technologies, vol. 353 SIST, Springer Science and Business Media Deutschland GmbH, pp. 154-163, 8th Brazilian Technology Symposium, BTSym 2022, Virtual, online, 24/10/22. https://doi.org/10.1007/978-3-031-31007-2_15

An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism. / Picón, Kevin; Rodriguez, Juan; Salazar-Gamarra, Rodrigo et al.
Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology. ed. / Yuzo Iano; Osamu Saotome; Guillermo Leopoldo Kemper Vásquez; Maria Thereza de Moraes Gomes Rosa; Rangel Arthur; Gabriel Gomes de Oliveira. Springer Science and Business Media Deutschland GmbH, 2023. p. 154-163 (Smart Innovation, Systems and Technologies; Vol. 353 SIST).

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

TY - GEN

T1 - An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism

AU - Picón, Kevin

AU - Rodriguez, Juan

AU - Salazar-Gamarra, Rodrigo

AU - Márquez, Manuel

AU - Kemper, Guillermo

PY - 2023

Y1 - 2023

N2 - This work proposes an algorithm to reconstruct 4 precordial electrocardiogram (ECG) lead signals. Standard cardiovascular disease (CVD) monitoring and detection uses all 12 available ECG leads. However, this number of leads implies a certain complexity of the equipment in terms of size, weight, and power consumption. Computational algorithms aimed at reducing the number of required leads for CVD detection help lower the time consumption and errors due to needing many signal acquisition cables. In this work, an LSTM sequence-to-sequence (Seq2Seq) neural network model with attention takes only 4 ECG leads (I, II, V2, and V5) and outputs the mentioned precordial leads. This proposal contributes to making ECG signal acquisitions easier and more accessible by requiring fewer cables and thus facilitating its use by people with little training. The model achieved a maximum average Pearson correlation coefficient of 0.9707 for all leads. It was validated using the PTB Diagnostic ECG Database.

AB - This work proposes an algorithm to reconstruct 4 precordial electrocardiogram (ECG) lead signals. Standard cardiovascular disease (CVD) monitoring and detection uses all 12 available ECG leads. However, this number of leads implies a certain complexity of the equipment in terms of size, weight, and power consumption. Computational algorithms aimed at reducing the number of required leads for CVD detection help lower the time consumption and errors due to needing many signal acquisition cables. In this work, an LSTM sequence-to-sequence (Seq2Seq) neural network model with attention takes only 4 ECG leads (I, II, V2, and V5) and outputs the mentioned precordial leads. This proposal contributes to making ECG signal acquisitions easier and more accessible by requiring fewer cables and thus facilitating its use by people with little training. The model achieved a maximum average Pearson correlation coefficient of 0.9707 for all leads. It was validated using the PTB Diagnostic ECG Database.

KW - Attention mechanism

KW - ECG leads

KW - LSTM

KW - Reconstruction

UR - https://www.scopus.com/pages/publications/85161407952

U2 - 10.1007/978-3-031-31007-2_15

DO - 10.1007/978-3-031-31007-2_15

M3 - Contribución a la conferencia

AN - SCOPUS:85161407952

SN - 9783031310065

T3 - Smart Innovation, Systems and Technologies

SP - 154

EP - 163

BT - Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology

A2 - Iano, Yuzo

A2 - Saotome, Osamu

A2 - Kemper Vásquez, Guillermo Leopoldo

A2 - de Moraes Gomes Rosa, Maria Thereza

A2 - Arthur, Rangel

A2 - Gomes de Oliveira, Gabriel

PB - Springer Science and Business Media Deutschland GmbH

T2 - 8th Brazilian Technology Symposium, BTSym 2022

Y2 - 24 October 2022 through 26 October 2022

ER -

Picón K, Rodriguez J, Salazar-Gamarra R, Márquez M, Kemper G. An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism. In Iano Y, Saotome O, Kemper Vásquez GL, de Moraes Gomes Rosa MT, Arthur R, Gomes de Oliveira G, editors, Proceedings of the 8th Brazilian Technology Symposium, BTSymn 2022 - Emerging Trends and Challenges in Technology. Springer Science and Business Media Deutschland GmbH. 2023. p. 154-163. (Smart Innovation, Systems and Technologies). doi: 10.1007/978-3-031-31007-2_15

An Algorithm for the Reconstruction of 4 ECG Lead Signals Based on the Attention Mechanism

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this