Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

ECG-Based Detection of Acute Myocardial Infarction Using a Wrist-Worn Device

Jančiulevičiūtė, Karolina ; Sokas, Daivaras ; Bacevičius, Justinas ; Sörnmo, Leif LU and Petrėnas, Andrius (2026) In IEEE Transactions on Biomedical Engineering 73(1). p.234-244
Abstract

Background: A wrist-worn wearable device for acquiring limb and chest ECG leads (wECG) may constitute a promising approach to detection of acute myocardial infarction (AMI). However, it remains to be demonstrated whether the information conveyed by the wECG is sufficient for AMI detection. Objective: To explore explainable machine learning models for detecting AMI using the wECG. Methods: Two types of machine learning models are explored: a convolutional neural network (CNN) using the raw ECG as input and a gradient-boosting decision tree (GBDT) using clinically informative features. 123 participants were included, divided into patients with AMI, patients with other cardiovascular diseases, and healthy individuals. A wrist-worn device... (More)

Background: A wrist-worn wearable device for acquiring limb and chest ECG leads (wECG) may constitute a promising approach to detection of acute myocardial infarction (AMI). However, it remains to be demonstrated whether the information conveyed by the wECG is sufficient for AMI detection. Objective: To explore explainable machine learning models for detecting AMI using the wECG. Methods: Two types of machine learning models are explored: a convolutional neural network (CNN) using the raw ECG as input and a gradient-boosting decision tree (GBDT) using clinically informative features. 123 participants were included, divided into patients with AMI, patients with other cardiovascular diseases, and healthy individuals. A wrist-worn device equipped with three biopotential electrodes was used to acquire two ECG leads with a single touch: limb lead I and another lead involving a specific body site, i.e., either the V3 or V5 electrode positions, or the abdomen. Results: The best performance on the test dataset is obtained using models that incorporate all four leads. The CNN model performs slightly better than the GBDT model, with a sensitivity of 0.77 and specificity of 0.75 compared to 0.77 and 0.72, respectively. When distinguishing between AMI and healthy participants, the specificity increases to 0.94 for the CNN model and 0.90 for the GBDT model. Feature importance analysis shows that the GBDT model primarily relies on the J point, while the CNN model primarily relies on the QRS complex. Conclusions: wECG-based AMI detection shows considerable promise in out-of-hospital settings. However, caution is needed as CNN explanations rarely agree with the ECG intervals typically analyzed in clinical practice.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
convolutional neural network, decision tree, explainability, interpretability, ST elevation, Wearable device
in
IEEE Transactions on Biomedical Engineering
volume
73
issue
1
pages
11 pages
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
external identifiers
  • pmid:40522809
  • scopus:105008567176
ISSN
0018-9294
DOI
10.1109/TBME.2025.3580154
language
English
LU publication?
yes
additional info
Publisher Copyright: © 1964-2012 IEEE.
id
f12923c9-2287-44e3-9a40-1e1a76c5f1f8
date added to LUP
2026-01-20 15:05:01
date last changed
2026-01-20 15:06:19
@article{f12923c9-2287-44e3-9a40-1e1a76c5f1f8,
  abstract     = {{<p>Background: A wrist-worn wearable device for acquiring limb and chest ECG leads (wECG) may constitute a promising approach to detection of acute myocardial infarction (AMI). However, it remains to be demonstrated whether the information conveyed by the wECG is sufficient for AMI detection. Objective: To explore explainable machine learning models for detecting AMI using the wECG. Methods: Two types of machine learning models are explored: a convolutional neural network (CNN) using the raw ECG as input and a gradient-boosting decision tree (GBDT) using clinically informative features. 123 participants were included, divided into patients with AMI, patients with other cardiovascular diseases, and healthy individuals. A wrist-worn device equipped with three biopotential electrodes was used to acquire two ECG leads with a single touch: limb lead I and another lead involving a specific body site, i.e., either the V3 or V5 electrode positions, or the abdomen. Results: The best performance on the test dataset is obtained using models that incorporate all four leads. The CNN model performs slightly better than the GBDT model, with a sensitivity of 0.77 and specificity of 0.75 compared to 0.77 and 0.72, respectively. When distinguishing between AMI and healthy participants, the specificity increases to 0.94 for the CNN model and 0.90 for the GBDT model. Feature importance analysis shows that the GBDT model primarily relies on the J point, while the CNN model primarily relies on the QRS complex. Conclusions: wECG-based AMI detection shows considerable promise in out-of-hospital settings. However, caution is needed as CNN explanations rarely agree with the ECG intervals typically analyzed in clinical practice.</p>}},
  author       = {{Jančiulevičiūtė, Karolina and Sokas, Daivaras and Bacevičius, Justinas and Sörnmo, Leif and Petrėnas, Andrius}},
  issn         = {{0018-9294}},
  keywords     = {{convolutional neural network; decision tree; explainability; interpretability; ST elevation; Wearable device}},
  language     = {{eng}},
  number       = {{1}},
  pages        = {{234--244}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{IEEE Transactions on Biomedical Engineering}},
  title        = {{ECG-Based Detection of Acute Myocardial Infarction Using a Wrist-Worn Device}},
  url          = {{http://dx.doi.org/10.1109/TBME.2025.3580154}},
  doi          = {{10.1109/TBME.2025.3580154}},
  volume       = {{73}},
  year         = {{2026}},
}