Open Access
Open access

Convolutional neural network (CNN)-enabled electrocardiogram (ECG) analysis: a comparison between standard twelve-lead and single-lead setups

Andrea Saglietto 1, 2, 3, 4
Daniele Baccega 5, 6, 7, 8
Roberto Esposito 5, 7
Matteo Anselmino 1, 2, 3, 4
Veronica Dusi 1, 2, 3, 4
Attilio Fiandrotti 5, 7
Gaetano Maria De Ferrari 1, 2, 3, 4
1
 
Division of Cardiology, Cardiovascular and Thoracic Department, “Citta Della Salute e Della Scienza” Hospital, Italy
3
 
Division of Cardiology, Cardiovascular and Thoracic Department, “Citta Della Salute E Della Scienza” Hospital, Turin, Italy
6
 
Laboratorio InfoLife, Consorzio Interuniversitario Nazionale per l'Informatica (CINI), Italy
8
 
Laboratorio InfoLife, Consorzio Interuniversitario Nazionale per l'Informatica (CINI), Rome, Italy
Publication typeJournal Article
Publication date2024-02-15
scimago Q1
wos Q2
SJR0.975
CiteScore5.5
Impact factor2.9
ISSN2297055X
Cardiology and Cardiovascular Medicine
Abstract
Background

Artificial intelligence (AI) has shown promise in the early detection of various cardiac conditions from a standard 12-lead electrocardiogram (ECG). However, the ability of AI to identify abnormalities from single-lead recordings across a range of pathological conditions remains to be systematically investigated. This study aims to assess the performance of a convolutional neural network (CNN) using a single-lead (D1) rather than a standard 12-lead setup for accurate identification of ECG abnormalities.

Methods

We designed and trained a lightweight CNN to identify 20 different cardiac abnormalities on ECGs, using data from the PTB-XL dataset. With a relatively simple architecture, the network was designed to accommodate different combinations of leads as input (<100,000 learnable parameters). We compared various lead setups such as the standard 12-lead, D1 alone, and D1 paired with an additional lead.

Results

The CNN based on single-lead ECG (D1) outperformed the one based on the standard 12-lead framework [with an average percentage difference of the area under the curve (AUC) of −8.7%]. Notably, for certain diagnostic classes, there was no difference in the diagnostic AUC between the single-lead and the standard 12-lead setups. When a second lead was detected in the CNN in addition to D1, the AUC gap was further reduced to an average percentage difference of −2.8% compared with that of the standard 12-lead setup.

Conclusions

A relatively lightweight CNN can predict different classes of cardiac abnormalities from D1 alone and the standard 12-lead ECG. Considering the growing availability of wearable devices capable of recording a D1-like single-lead ECG, we discuss how our findings contribute to the foundation of a large-scale screening of cardiac abnormalities.

Found 
Found 

Top-30

Journals

1
Bioelectronic Medicine
1 publication, 20%
IEEE Access
1 publication, 20%
Science China Materials
1 publication, 20%
Expert Systems with Applications
1 publication, 20%
1

Publishers

1
2
Springer Nature
2 publications, 40%
Institute of Electrical and Electronics Engineers (IEEE)
2 publications, 40%
Elsevier
1 publication, 20%
1
2
  • We do not take into account publications without a DOI.
  • Statistics recalculated weekly.

Are you a researcher?

Create a profile to get free access to personal recommendations for colleagues and new articles.
Metrics
5
Share
Cite this
GOST |
Cite this
GOST Copy
Saglietto A. et al. Convolutional neural network (CNN)-enabled electrocardiogram (ECG) analysis: a comparison between standard twelve-lead and single-lead setups // Frontiers in Cardiovascular Medicine. 2024. Vol. 11.
GOST all authors (up to 50) Copy
Saglietto A., Baccega D., Esposito R., Anselmino M., Dusi V., Fiandrotti A., De Ferrari G. M. Convolutional neural network (CNN)-enabled electrocardiogram (ECG) analysis: a comparison between standard twelve-lead and single-lead setups // Frontiers in Cardiovascular Medicine. 2024. Vol. 11.
RIS |
Cite this
RIS Copy
TY - JOUR
DO - 10.3389/fcvm.2024.1327179
UR - https://www.frontiersin.org/articles/10.3389/fcvm.2024.1327179/full
TI - Convolutional neural network (CNN)-enabled electrocardiogram (ECG) analysis: a comparison between standard twelve-lead and single-lead setups
T2 - Frontiers in Cardiovascular Medicine
AU - Saglietto, Andrea
AU - Baccega, Daniele
AU - Esposito, Roberto
AU - Anselmino, Matteo
AU - Dusi, Veronica
AU - Fiandrotti, Attilio
AU - De Ferrari, Gaetano Maria
PY - 2024
DA - 2024/02/15
PB - Frontiers Media S.A.
VL - 11
PMID - 38426118
SN - 2297-055X
ER -
BibTex
Cite this
BibTex (up to 50 authors) Copy
@article{2024_Saglietto,
author = {Andrea Saglietto and Daniele Baccega and Roberto Esposito and Matteo Anselmino and Veronica Dusi and Attilio Fiandrotti and Gaetano Maria De Ferrari},
title = {Convolutional neural network (CNN)-enabled electrocardiogram (ECG) analysis: a comparison between standard twelve-lead and single-lead setups},
journal = {Frontiers in Cardiovascular Medicine},
year = {2024},
volume = {11},
publisher = {Frontiers Media S.A.},
month = {feb},
url = {https://www.frontiersin.org/articles/10.3389/fcvm.2024.1327179/full},
doi = {10.3389/fcvm.2024.1327179}
}