Cargando…

Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset

The electrocardiogram (ECG) is considered a fundamental of cardiology. The ECG consists of P, QRS, and T waves. Information provided from the signal based on the intervals and amplitudes of these waves is associated with various heart diseases. The first step in isolating the features of an ECG begi...

Descripción completa

Detalles Bibliográficos
Autores principales: Pałczyński, Krzysztof, Śmigiel, Sandra, Ledziński, Damian, Bujnowski, Sławomir
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839938/
https://www.ncbi.nlm.nih.gov/pubmed/35161650
http://dx.doi.org/10.3390/s22030904
_version_ 1784650494415732736
author Pałczyński, Krzysztof
Śmigiel, Sandra
Ledziński, Damian
Bujnowski, Sławomir
author_facet Pałczyński, Krzysztof
Śmigiel, Sandra
Ledziński, Damian
Bujnowski, Sławomir
author_sort Pałczyński, Krzysztof
collection PubMed
description The electrocardiogram (ECG) is considered a fundamental of cardiology. The ECG consists of P, QRS, and T waves. Information provided from the signal based on the intervals and amplitudes of these waves is associated with various heart diseases. The first step in isolating the features of an ECG begins with the accurate detection of the R-peaks in the QRS complex. The database was based on the PTB-XL database, and the signals from Lead I–XII were analyzed. This research focuses on determining the Few-Shot Learning (FSL) applicability for ECG signal proximity-based classification. The study was conducted by training Deep Convolutional Neural Networks to recognize 2, 5, and 20 different heart disease classes. The results of the FSL network were compared with the evaluation score of the neural network performing softmax-based classification. The neural network proposed for this task interprets a set of QRS complexes extracted from ECG signals. The FSL network proved to have higher accuracy in classifying healthy/sick patients ranging from 93.2% to 89.2% than the softmax-based classification network, which achieved 90.5–89.2% accuracy. The proposed network also achieved better results in classifying five different disease classes than softmax-based counterparts with an accuracy of 80.2–77.9% as opposed to 77.1% to 75.1%. In addition, the method of R-peaks labeling and QRS complexes extraction has been implemented. This procedure converts a 12-lead signal into a set of R waves by using the detection algorithms and the k-mean algorithm.
format Online
Article
Text
id pubmed-8839938
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-88399382022-02-13 Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset Pałczyński, Krzysztof Śmigiel, Sandra Ledziński, Damian Bujnowski, Sławomir Sensors (Basel) Article The electrocardiogram (ECG) is considered a fundamental of cardiology. The ECG consists of P, QRS, and T waves. Information provided from the signal based on the intervals and amplitudes of these waves is associated with various heart diseases. The first step in isolating the features of an ECG begins with the accurate detection of the R-peaks in the QRS complex. The database was based on the PTB-XL database, and the signals from Lead I–XII were analyzed. This research focuses on determining the Few-Shot Learning (FSL) applicability for ECG signal proximity-based classification. The study was conducted by training Deep Convolutional Neural Networks to recognize 2, 5, and 20 different heart disease classes. The results of the FSL network were compared with the evaluation score of the neural network performing softmax-based classification. The neural network proposed for this task interprets a set of QRS complexes extracted from ECG signals. The FSL network proved to have higher accuracy in classifying healthy/sick patients ranging from 93.2% to 89.2% than the softmax-based classification network, which achieved 90.5–89.2% accuracy. The proposed network also achieved better results in classifying five different disease classes than softmax-based counterparts with an accuracy of 80.2–77.9% as opposed to 77.1% to 75.1%. In addition, the method of R-peaks labeling and QRS complexes extraction has been implemented. This procedure converts a 12-lead signal into a set of R waves by using the detection algorithms and the k-mean algorithm. MDPI 2022-01-25 /pmc/articles/PMC8839938/ /pubmed/35161650 http://dx.doi.org/10.3390/s22030904 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pałczyński, Krzysztof
Śmigiel, Sandra
Ledziński, Damian
Bujnowski, Sławomir
Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title_full Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title_fullStr Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title_full_unstemmed Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title_short Study of the Few-Shot Learning for ECG Classification Based on the PTB-XL Dataset
title_sort study of the few-shot learning for ecg classification based on the ptb-xl dataset
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8839938/
https://www.ncbi.nlm.nih.gov/pubmed/35161650
http://dx.doi.org/10.3390/s22030904
work_keys_str_mv AT pałczynskikrzysztof studyofthefewshotlearningforecgclassificationbasedontheptbxldataset
AT smigielsandra studyofthefewshotlearningforecgclassificationbasedontheptbxldataset
AT ledzinskidamian studyofthefewshotlearningforecgclassificationbasedontheptbxldataset
AT bujnowskisławomir studyofthefewshotlearningforecgclassificationbasedontheptbxldataset