Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification
Background Electrocardiogram (ECG) signal classification plays a critical role in the automatic diagnosis of heart abnormalities. While most ECG signal patterns cannot be recognized by a human interpreter, they can be detected with precision using artificial intelligence approaches, making the ECG a...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2022-01-01
|
| Series: | PeerJ Computer Science |
| Subjects: | |
| Online Access: | https://peerj.com/articles/cs-825.pdf |
| _version_ | 1818957596576448512 |
|---|---|
| author | Annisa Darmawahyuni Siti Nurmaini Muhammad Naufal Rachmatullah Bambang Tutuko Ade Iriani Sapitri Firdaus Firdaus Ahmad Fansyuri Aldi Predyansyah |
| author_facet | Annisa Darmawahyuni Siti Nurmaini Muhammad Naufal Rachmatullah Bambang Tutuko Ade Iriani Sapitri Firdaus Firdaus Ahmad Fansyuri Aldi Predyansyah |
| author_sort | Annisa Darmawahyuni |
| collection | DOAJ |
| description | Background Electrocardiogram (ECG) signal classification plays a critical role in the automatic diagnosis of heart abnormalities. While most ECG signal patterns cannot be recognized by a human interpreter, they can be detected with precision using artificial intelligence approaches, making the ECG a powerful non-invasive biomarker. However, performing rapid and accurate ECG signal classification is difficult due to the low amplitude, complexity, and non-linearity. The widely-available deep learning (DL) method we propose has presented an opportunity to substantially improve the accuracy of automated ECG classification analysis using rhythm or beat features. Unfortunately, a comprehensive and general evaluation of the specific DL architecture for ECG analysis across a wide variety of rhythm and beat features has not been previously reported. Some previous studies have been concerned with detecting ECG class abnormalities only through rhythm or beat features separately. Methods This study proposes a single architecture based on the DL method with one-dimensional convolutional neural network (1D-CNN) architecture, to automatically classify 24 patterns of ECG signals through both rhythm and beat. To validate the proposed model, five databases which consisted of nine-class of ECG-base rhythm and 15-class of ECG-based beat were used in this study. The proposed DL network was applied and studied with varying datasets with different frequency samplings in intra and inter-patient scheme. Results Using a 10-fold cross-validation scheme, the performance results had an accuracy of 99.98%, a sensitivity of 99.90%, a specificity of 99.89%, a precision of 99.90%, and an F1-score of 99.99% for ECG rhythm classification. Additionally, for ECG beat classification, the model obtained an accuracy of 99.87%, a sensitivity of 96.97%, a specificity of 99.89%, a precision of 92.23%, and an F1-score of 94.39%. In conclusion, this study provides clinicians with an advanced methodology for detecting and discriminating heart abnormalities between different ECG rhythm and beat assessments by using one outstanding proposed DL architecture. |
| first_indexed | 2024-12-20T11:12:22Z |
| format | Article |
| id | doaj.art-78a313a1bb8b463f9933044694ad10a9 |
| institution | Directory Open Access Journal |
| issn | 2376-5992 |
| language | English |
| last_indexed | 2024-12-20T11:12:22Z |
| publishDate | 2022-01-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ Computer Science |
| spelling | doaj.art-78a313a1bb8b463f9933044694ad10a92022-12-21T19:42:43ZengPeerJ Inc.PeerJ Computer Science2376-59922022-01-018e82510.7717/peerj-cs.825Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classificationAnnisa Darmawahyuni0Siti Nurmaini1Muhammad Naufal Rachmatullah2Bambang Tutuko3Ade Iriani Sapitri4Firdaus Firdaus5Ahmad Fansyuri6Aldi Predyansyah7Intelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaIntelligent System Research Group, Faculty of Computer Science, Universitas Sriwijaya, Palembang, IndonesiaBackground Electrocardiogram (ECG) signal classification plays a critical role in the automatic diagnosis of heart abnormalities. While most ECG signal patterns cannot be recognized by a human interpreter, they can be detected with precision using artificial intelligence approaches, making the ECG a powerful non-invasive biomarker. However, performing rapid and accurate ECG signal classification is difficult due to the low amplitude, complexity, and non-linearity. The widely-available deep learning (DL) method we propose has presented an opportunity to substantially improve the accuracy of automated ECG classification analysis using rhythm or beat features. Unfortunately, a comprehensive and general evaluation of the specific DL architecture for ECG analysis across a wide variety of rhythm and beat features has not been previously reported. Some previous studies have been concerned with detecting ECG class abnormalities only through rhythm or beat features separately. Methods This study proposes a single architecture based on the DL method with one-dimensional convolutional neural network (1D-CNN) architecture, to automatically classify 24 patterns of ECG signals through both rhythm and beat. To validate the proposed model, five databases which consisted of nine-class of ECG-base rhythm and 15-class of ECG-based beat were used in this study. The proposed DL network was applied and studied with varying datasets with different frequency samplings in intra and inter-patient scheme. Results Using a 10-fold cross-validation scheme, the performance results had an accuracy of 99.98%, a sensitivity of 99.90%, a specificity of 99.89%, a precision of 99.90%, and an F1-score of 99.99% for ECG rhythm classification. Additionally, for ECG beat classification, the model obtained an accuracy of 99.87%, a sensitivity of 96.97%, a specificity of 99.89%, a precision of 92.23%, and an F1-score of 94.39%. In conclusion, this study provides clinicians with an advanced methodology for detecting and discriminating heart abnormalities between different ECG rhythm and beat assessments by using one outstanding proposed DL architecture.https://peerj.com/articles/cs-825.pdfDeep learningElectrocardiogramHeart rhythmHeart beatConvolutional neural networkClassification |
| spellingShingle | Annisa Darmawahyuni Siti Nurmaini Muhammad Naufal Rachmatullah Bambang Tutuko Ade Iriani Sapitri Firdaus Firdaus Ahmad Fansyuri Aldi Predyansyah Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification PeerJ Computer Science Deep learning Electrocardiogram Heart rhythm Heart beat Convolutional neural network Classification |
| title | Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification |
| title_full | Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification |
| title_fullStr | Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification |
| title_full_unstemmed | Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification |
| title_short | Deep learning-based electrocardiogram rhythm and beat features for heart abnormality classification |
| title_sort | deep learning based electrocardiogram rhythm and beat features for heart abnormality classification |
| topic | Deep learning Electrocardiogram Heart rhythm Heart beat Convolutional neural network Classification |
| url | https://peerj.com/articles/cs-825.pdf |
| work_keys_str_mv | AT annisadarmawahyuni deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT sitinurmaini deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT muhammadnaufalrachmatullah deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT bambangtutuko deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT adeirianisapitri deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT firdausfirdaus deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT ahmadfansyuri deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification AT aldipredyansyah deeplearningbasedelectrocardiogramrhythmandbeatfeaturesforheartabnormalityclassification |