An echo state network for synthesizing the standard 12-lead ECG from a two-lead ECG obtained from a single touch of a wrist-worn device
(2025) In Biomedical Signal Processing and Control 109.- Abstract
Background: With the availability of a wrist-worn device capable of acquiring two ECG leads with a single touch, synthesis of the 12-lead ECG may be accomplished to facilitate clinical interpretation. Objective: This study proposes an echo state network (ESN) for synthesizing the 12-lead ECG from two leads simultaneously acquired using a wrist-worn device. Methods: The wrist-worn device, equipped with three electrodes, was used to acquire two ECG leads from 51 healthy participants, 29 patients with acute myocardial infarction, and 12 patients with other cardiovascular diseases. The person-specific synthesis is based on the ESN, a recurrent neural network, trained on a single resting, standard 12-lead ECG through a highly efficient... (More)
Background: With the availability of a wrist-worn device capable of acquiring two ECG leads with a single touch, synthesis of the 12-lead ECG may be accomplished to facilitate clinical interpretation. Objective: This study proposes an echo state network (ESN) for synthesizing the 12-lead ECG from two leads simultaneously acquired using a wrist-worn device. Methods: The wrist-worn device, equipped with three electrodes, was used to acquire two ECG leads from 51 healthy participants, 29 patients with acute myocardial infarction, and 12 patients with other cardiovascular diseases. The person-specific synthesis is based on the ESN, a recurrent neural network, trained on a single resting, standard 12-lead ECG through a highly efficient training process. To explore the importance of different electrode touch sites, the participants were instructed to touch sites on the body corresponding to the electrode positions for acquiring the precordial leads V3 and V5, as well as the abdomen. Results: Using the ESN, the lowest RMS error between the standard and the synthesized ECGs is obtained for leads I and V1, irrespective of participant group and touch site from which the two-lead ECG was acquired. The ESN outperformed a linear regression-based transformation matrix, especially for the precordial leads where the RMS error was up to three times higher than that of the ESN. Conclusion: ESN-based synthesis of the 12-lead ECG based on a two-lead ECG holds promise as a valuable tool for screening abnormalities in the ECG.
(Less)
- author
- Jančiulevičiūtė, Karolina ; Sokas, Daivaras ; Daukantas, Saulius ; Sörnmo, Leif LU and Petrėnas, Andrius
- organization
- publishing date
- 2025-11
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- Machine learning, Myocardial infarction, Person-specific model, Reduced lead systems, Reservoir computing
- in
- Biomedical Signal Processing and Control
- volume
- 109
- article number
- 108008
- publisher
- Elsevier
- external identifiers
-
- scopus:105005184923
- ISSN
- 1746-8094
- DOI
- 10.1016/j.bspc.2025.108008
- language
- English
- LU publication?
- yes
- id
- b85a01da-8bbd-4439-baaf-ba7b5b8c077e
- date added to LUP
- 2025-07-15 10:41:14
- date last changed
- 2025-07-15 10:41:31
@article{b85a01da-8bbd-4439-baaf-ba7b5b8c077e,
abstract = {{<p>Background: With the availability of a wrist-worn device capable of acquiring two ECG leads with a single touch, synthesis of the 12-lead ECG may be accomplished to facilitate clinical interpretation. Objective: This study proposes an echo state network (ESN) for synthesizing the 12-lead ECG from two leads simultaneously acquired using a wrist-worn device. Methods: The wrist-worn device, equipped with three electrodes, was used to acquire two ECG leads from 51 healthy participants, 29 patients with acute myocardial infarction, and 12 patients with other cardiovascular diseases. The person-specific synthesis is based on the ESN, a recurrent neural network, trained on a single resting, standard 12-lead ECG through a highly efficient training process. To explore the importance of different electrode touch sites, the participants were instructed to touch sites on the body corresponding to the electrode positions for acquiring the precordial leads V3 and V5, as well as the abdomen. Results: Using the ESN, the lowest RMS error between the standard and the synthesized ECGs is obtained for leads I and V1, irrespective of participant group and touch site from which the two-lead ECG was acquired. The ESN outperformed a linear regression-based transformation matrix, especially for the precordial leads where the RMS error was up to three times higher than that of the ESN. Conclusion: ESN-based synthesis of the 12-lead ECG based on a two-lead ECG holds promise as a valuable tool for screening abnormalities in the ECG.</p>}},
author = {{Jančiulevičiūtė, Karolina and Sokas, Daivaras and Daukantas, Saulius and Sörnmo, Leif and Petrėnas, Andrius}},
issn = {{1746-8094}},
keywords = {{Machine learning; Myocardial infarction; Person-specific model; Reduced lead systems; Reservoir computing}},
language = {{eng}},
publisher = {{Elsevier}},
series = {{Biomedical Signal Processing and Control}},
title = {{An echo state network for synthesizing the standard 12-lead ECG from a two-lead ECG obtained from a single touch of a wrist-worn device}},
url = {{http://dx.doi.org/10.1016/j.bspc.2025.108008}},
doi = {{10.1016/j.bspc.2025.108008}},
volume = {{109}},
year = {{2025}},
}