PTB-XL+, a comprehensive electrocardiographic feature dataset

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

PTB-XL+, a comprehensive electrocardiographic feature dataset. / Strodthoff, Nils; Mehari, Temesgen; Nagel, Claudia; Aston, Philip J.; Sundar, Ashish; Graff, Claus; Kanters, Jørgen K.; Haverkamp, Wilhelm; Dössel, Olaf; Loewe, Axel; Bär, Markus; Schaeffter, Tobias.

I: Scientific Data, Bind 10, 279, 2023.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Strodthoff, N, Mehari, T, Nagel, C, Aston, PJ, Sundar, A, Graff, C, Kanters, JK, Haverkamp, W, Dössel, O, Loewe, A, Bär, M & Schaeffter, T 2023, 'PTB-XL+, a comprehensive electrocardiographic feature dataset', Scientific Data, bind 10, 279. https://doi.org/10.1038/s41597-023-02153-8

APA

Strodthoff, N., Mehari, T., Nagel, C., Aston, P. J., Sundar, A., Graff, C., Kanters, J. K., Haverkamp, W., Dössel, O., Loewe, A., Bär, M., & Schaeffter, T. (2023). PTB-XL+, a comprehensive electrocardiographic feature dataset. Scientific Data, 10, [279]. https://doi.org/10.1038/s41597-023-02153-8

Vancouver

Strodthoff N, Mehari T, Nagel C, Aston PJ, Sundar A, Graff C o.a. PTB-XL+, a comprehensive electrocardiographic feature dataset. Scientific Data. 2023;10. 279. https://doi.org/10.1038/s41597-023-02153-8

Author

Strodthoff, Nils ; Mehari, Temesgen ; Nagel, Claudia ; Aston, Philip J. ; Sundar, Ashish ; Graff, Claus ; Kanters, Jørgen K. ; Haverkamp, Wilhelm ; Dössel, Olaf ; Loewe, Axel ; Bär, Markus ; Schaeffter, Tobias. / PTB-XL+, a comprehensive electrocardiographic feature dataset. I: Scientific Data. 2023 ; Bind 10.

Bibtex

@article{40a7e01d77ff475ebb88aaa95322875d,

title = "PTB-XL+, a comprehensive electrocardiographic feature dataset",

abstract = "Machine learning (ML) methods for the analysis of electrocardiography (ECG) data are gaining importance, substantially supported by the release of large public datasets. However, these current datasets miss important derived descriptors such as ECG features that have been devised in the past hundred years and still form the basis of most automatic ECG analysis algorithms and are critical for cardiologists{\textquoteright} decision processes. ECG features are available from sophisticated commercial software but are not accessible to the general public. To alleviate this issue, we add ECG features from two leading commercial algorithms and an open-source implementation supplemented by a set of automatic diagnostic statements from a commercial ECG analysis software in preprocessed format. This allows the comparison of ML models trained on clinically versus automatically generated label sets. We provide an extensive technical validation of features and diagnostic statements for ML applications. We believe this release crucially enhances the usability of the PTB-XL dataset as a reference dataset for ML methods in the context of ECG data.",

author = "Nils Strodthoff and Temesgen Mehari and Claudia Nagel and Aston, {Philip J.} and Ashish Sundar and Claus Graff and Kanters, {J{\o}rgen K.} and Wilhelm Haverkamp and Olaf D{\"o}ssel and Axel Loewe and Markus B{\"a}r and Tobias Schaeffter",

note = "Publisher Copyright: {\textcopyright} 2023, The Author(s).",

year = "2023",

doi = "10.1038/s41597-023-02153-8",

language = "English",

volume = "10",

journal = "Scientific data",

issn = "2052-4463",

publisher = "nature publishing group",

}

RIS

TY - JOUR

T1 - PTB-XL+, a comprehensive electrocardiographic feature dataset

AU - Strodthoff, Nils

AU - Mehari, Temesgen

AU - Nagel, Claudia

AU - Aston, Philip J.

AU - Sundar, Ashish

AU - Graff, Claus

AU - Kanters, Jørgen K.

AU - Haverkamp, Wilhelm

AU - Dössel, Olaf

AU - Loewe, Axel

AU - Bär, Markus

AU - Schaeffter, Tobias

PY - 2023

Y1 - 2023

N2 - Machine learning (ML) methods for the analysis of electrocardiography (ECG) data are gaining importance, substantially supported by the release of large public datasets. However, these current datasets miss important derived descriptors such as ECG features that have been devised in the past hundred years and still form the basis of most automatic ECG analysis algorithms and are critical for cardiologists’ decision processes. ECG features are available from sophisticated commercial software but are not accessible to the general public. To alleviate this issue, we add ECG features from two leading commercial algorithms and an open-source implementation supplemented by a set of automatic diagnostic statements from a commercial ECG analysis software in preprocessed format. This allows the comparison of ML models trained on clinically versus automatically generated label sets. We provide an extensive technical validation of features and diagnostic statements for ML applications. We believe this release crucially enhances the usability of the PTB-XL dataset as a reference dataset for ML methods in the context of ECG data.

AB - Machine learning (ML) methods for the analysis of electrocardiography (ECG) data are gaining importance, substantially supported by the release of large public datasets. However, these current datasets miss important derived descriptors such as ECG features that have been devised in the past hundred years and still form the basis of most automatic ECG analysis algorithms and are critical for cardiologists’ decision processes. ECG features are available from sophisticated commercial software but are not accessible to the general public. To alleviate this issue, we add ECG features from two leading commercial algorithms and an open-source implementation supplemented by a set of automatic diagnostic statements from a commercial ECG analysis software in preprocessed format. This allows the comparison of ML models trained on clinically versus automatically generated label sets. We provide an extensive technical validation of features and diagnostic statements for ML applications. We believe this release crucially enhances the usability of the PTB-XL dataset as a reference dataset for ML methods in the context of ECG data.

U2 - 10.1038/s41597-023-02153-8

DO - 10.1038/s41597-023-02153-8

M3 - Journal article

C2 - 37179420

AN - SCOPUS:85159149325

VL - 10

JO - Scientific data

JF - Scientific data

SN - 2052-4463

M1 - 279

ER -

ID: 370737193

Biomedicinsk Institut