ECG-Based Identification of Sudden Cardiac Death through Sparse Representations
Sudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/22/7666 |
| _version_ | 1827675357114793984 |
|---|---|
| author | Josue R. Velázquez-González Hayde Peregrina-Barreto Jose J. Rangel-Magdaleno Juan M. Ramirez-Cortes Juan P. Amezquita-Sanchez |
| author_facet | Josue R. Velázquez-González Hayde Peregrina-Barreto Jose J. Rangel-Magdaleno Juan M. Ramirez-Cortes Juan P. Amezquita-Sanchez |
| author_sort | Josue R. Velázquez-González |
| collection | DOAJ |
| description | Sudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to a reference signal (healthy), then it is possible to indicate in advance a possible SCD occurrence. This work proposes SCD identification using Electrocardiogram (ECG) signals and a sparse representation technique. Moreover, the use of fixed feature ranking is avoided by considering a dictionary as a flexible set of features where each sparse representation could be seen as a dynamic feature extraction process. In this way, the involved features may differ within the dictionary’s margin of similarity, which is better-suited to the large number of variations that an ECG signal contains. The experiments were carried out using the ECG signals from the MIT/BIH-SCDH and the MIT/BIH-NSR databases. The results show that it is possible to achieve a detection 30 min before the SCD event occurs, reaching an an accuracy of 95.3% under the common scheme, and 80.5% under the proposed multi-class scheme, thus being suitable for detecting a SCD episode in advance. |
| first_indexed | 2024-03-10T05:03:56Z |
| format | Article |
| id | doaj.art-3a1812e0fa20449bb13aef89e67ddd31 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T05:03:56Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-3a1812e0fa20449bb13aef89e67ddd312023-11-23T01:27:39ZengMDPI AGSensors1424-82202021-11-012122766610.3390/s21227666ECG-Based Identification of Sudden Cardiac Death through Sparse RepresentationsJosue R. Velázquez-González0Hayde Peregrina-Barreto1Jose J. Rangel-Magdaleno2Juan M. Ramirez-Cortes3Juan P. Amezquita-Sanchez4Department of Computational Science, National Institute of Astrophysics, Optics, and Electronics, Santa Maria Tonantzintla, Puebla 72840, MexicoDepartment of Computational Science, National Institute of Astrophysics, Optics, and Electronics, Santa Maria Tonantzintla, Puebla 72840, MexicoDepartment of Electronics, National Institute of Astrophysics, Optics, and Electronics, Santa Maria Tonantzintla, Puebla 72840, MexicoDepartment of Electronics, National Institute of Astrophysics, Optics, and Electronics, Santa Maria Tonantzintla, Puebla 72840, MexicoFacultad de Ingeniería, Universidad Autónoma de Querétaro, Av Río Moctezuma 249, San Juan del Rio 76807, MexicoSudden Cardiac Death (SCD) is an unexpected sudden death due to a loss of heart function and represents more than 50% of the deaths from cardiovascular diseases. Since cardiovascular problems change the features in the electrical signal of the heart, if significant changes are found with respect to a reference signal (healthy), then it is possible to indicate in advance a possible SCD occurrence. This work proposes SCD identification using Electrocardiogram (ECG) signals and a sparse representation technique. Moreover, the use of fixed feature ranking is avoided by considering a dictionary as a flexible set of features where each sparse representation could be seen as a dynamic feature extraction process. In this way, the involved features may differ within the dictionary’s margin of similarity, which is better-suited to the large number of variations that an ECG signal contains. The experiments were carried out using the ECG signals from the MIT/BIH-SCDH and the MIT/BIH-NSR databases. The results show that it is possible to achieve a detection 30 min before the SCD event occurs, reaching an an accuracy of 95.3% under the common scheme, and 80.5% under the proposed multi-class scheme, thus being suitable for detecting a SCD episode in advance.https://www.mdpi.com/1424-8220/21/22/7666ECG signalssparse representationssudden cardiac death |
| spellingShingle | Josue R. Velázquez-González Hayde Peregrina-Barreto Jose J. Rangel-Magdaleno Juan M. Ramirez-Cortes Juan P. Amezquita-Sanchez ECG-Based Identification of Sudden Cardiac Death through Sparse Representations Sensors ECG signals sparse representations sudden cardiac death |
| title | ECG-Based Identification of Sudden Cardiac Death through Sparse Representations |
| title_full | ECG-Based Identification of Sudden Cardiac Death through Sparse Representations |
| title_fullStr | ECG-Based Identification of Sudden Cardiac Death through Sparse Representations |
| title_full_unstemmed | ECG-Based Identification of Sudden Cardiac Death through Sparse Representations |
| title_short | ECG-Based Identification of Sudden Cardiac Death through Sparse Representations |
| title_sort | ecg based identification of sudden cardiac death through sparse representations |
| topic | ECG signals sparse representations sudden cardiac death |
| url | https://www.mdpi.com/1424-8220/21/22/7666 |
| work_keys_str_mv | AT josuervelazquezgonzalez ecgbasedidentificationofsuddencardiacdeaththroughsparserepresentations AT haydeperegrinabarreto ecgbasedidentificationofsuddencardiacdeaththroughsparserepresentations AT josejrangelmagdaleno ecgbasedidentificationofsuddencardiacdeaththroughsparserepresentations AT juanmramirezcortes ecgbasedidentificationofsuddencardiacdeaththroughsparserepresentations AT juanpamezquitasanchez ecgbasedidentificationofsuddencardiacdeaththroughsparserepresentations |