Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs
The spatial QRS-T angle is a promising health indicator for risk stratification of sudden cardiac death (SCD). Thus far, the angle is estimated solely from 12-lead electrocardiogram (ECG) systems uncomfortable for ambulatory monitoring. Methods to estimate QRS-T angles from reduced-lead ECGs registe...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/14/5414 |
| _version_ | 1797415926183755776 |
|---|---|
| author | Ana Santos Rodrigues Rytis Augustauskas Mantas Lukoševičius Pablo Laguna Vaidotas Marozas |
| author_facet | Ana Santos Rodrigues Rytis Augustauskas Mantas Lukoševičius Pablo Laguna Vaidotas Marozas |
| author_sort | Ana Santos Rodrigues |
| collection | DOAJ |
| description | The spatial QRS-T angle is a promising health indicator for risk stratification of sudden cardiac death (SCD). Thus far, the angle is estimated solely from 12-lead electrocardiogram (ECG) systems uncomfortable for ambulatory monitoring. Methods to estimate QRS-T angles from reduced-lead ECGs registered with consumer healthcare devices would, therefore, facilitate ambulatory monitoring. (1) Objective: Develop a method to estimate spatial QRS-T angles from reduced-lead ECGs. (2) Approach: We designed a deep learning model to locate the QRS and T wave vectors necessary for computing the QRS-T angle. We implemented an original loss function to guide the model in the 3D space to search for each vector’s coordinates. A gradual reduction of ECG leads from the largest publicly available dataset of clinical 12-lead ECG recordings (<i>PTB-XL</i>) is used for training and validation. (3) Results: The spatial QRS-T angle can be estimated from leads {<i>I</i>, <i>II</i>, <i>aVF</i>, <i>V2</i>} with sufficient accuracy (absolute mean and median errors of 11.4° and 7.3°) for detecting abnormal angles without sacrificing patient comfortability. (4) Significance: Our model could enable ambulatory monitoring of spatial QRS-T angles using patch- or textile-based ECG devices. Populations at risk of SCD, like chronic cardiac and kidney disease patients, might benefit from this technology. |
| first_indexed | 2024-03-09T05:55:32Z |
| format | Article |
| id | doaj.art-a341bd911bbc46518866f21511b85059 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T05:55:32Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-a341bd911bbc46518866f21511b850592023-12-03T12:13:44ZengMDPI AGSensors1424-82202022-07-012214541410.3390/s22145414Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGsAna Santos Rodrigues0Rytis Augustauskas1Mantas Lukoševičius2Pablo Laguna3Vaidotas Marozas4Biomedical Engineering Institute, Kaunas University of Technology, 51423 Kaunas, LithuaniaDepartment of Automation, Kaunas University of Technology, 51367 Kaunas, LithuaniaFaculty of Informatics, Kaunas University of Technology, 51368 Kaunas, LithuaniaBiomedical Signal Interpretation and Computational Simulation (BSICoS) Group, Aragón Institute of Engineering Research (I3A), IIS Aragón, University of Zaragoza, 50018 Zaragoza, SpainBiomedical Engineering Institute, Kaunas University of Technology, 51423 Kaunas, LithuaniaThe spatial QRS-T angle is a promising health indicator for risk stratification of sudden cardiac death (SCD). Thus far, the angle is estimated solely from 12-lead electrocardiogram (ECG) systems uncomfortable for ambulatory monitoring. Methods to estimate QRS-T angles from reduced-lead ECGs registered with consumer healthcare devices would, therefore, facilitate ambulatory monitoring. (1) Objective: Develop a method to estimate spatial QRS-T angles from reduced-lead ECGs. (2) Approach: We designed a deep learning model to locate the QRS and T wave vectors necessary for computing the QRS-T angle. We implemented an original loss function to guide the model in the 3D space to search for each vector’s coordinates. A gradual reduction of ECG leads from the largest publicly available dataset of clinical 12-lead ECG recordings (<i>PTB-XL</i>) is used for training and validation. (3) Results: The spatial QRS-T angle can be estimated from leads {<i>I</i>, <i>II</i>, <i>aVF</i>, <i>V2</i>} with sufficient accuracy (absolute mean and median errors of 11.4° and 7.3°) for detecting abnormal angles without sacrificing patient comfortability. (4) Significance: Our model could enable ambulatory monitoring of spatial QRS-T angles using patch- or textile-based ECG devices. Populations at risk of SCD, like chronic cardiac and kidney disease patients, might benefit from this technology.https://www.mdpi.com/1424-8220/22/14/5414wearable devicesconsumer healthcare devicescardiovascular heath assessmentunobtrusive monitoringmachine learningregression |
| spellingShingle | Ana Santos Rodrigues Rytis Augustauskas Mantas Lukoševičius Pablo Laguna Vaidotas Marozas Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs Sensors wearable devices consumer healthcare devices cardiovascular heath assessment unobtrusive monitoring machine learning regression |
| title | Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs |
| title_full | Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs |
| title_fullStr | Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs |
| title_full_unstemmed | Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs |
| title_short | Deep-Learning-Based Estimation of the Spatial QRS-T Angle from Reduced-Lead ECGs |
| title_sort | deep learning based estimation of the spatial qrs t angle from reduced lead ecgs |
| topic | wearable devices consumer healthcare devices cardiovascular heath assessment unobtrusive monitoring machine learning regression |
| url | https://www.mdpi.com/1424-8220/22/14/5414 |
| work_keys_str_mv | AT anasantosrodrigues deeplearningbasedestimationofthespatialqrstanglefromreducedleadecgs AT rytisaugustauskas deeplearningbasedestimationofthespatialqrstanglefromreducedleadecgs AT mantaslukosevicius deeplearningbasedestimationofthespatialqrstanglefromreducedleadecgs AT pablolaguna deeplearningbasedestimationofthespatialqrstanglefromreducedleadecgs AT vaidotasmarozas deeplearningbasedestimationofthespatialqrstanglefromreducedleadecgs |