Automated Atrial Fibrillation Detection with ECG
An electrocardiography system records electrical activities of the heart, and it is used to assist doctors in the diagnosis of cardiac arrhythmia such as atrial fibrillation. This study presents a fast, automated deep-learning algorithm that predicts atrial fibrillation with excellent performance (F...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Bioengineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2306-5354/9/10/523 |
| _version_ | 1827651602983419904 |
|---|---|
| author | Ting-Ruen Wei Senbao Lu Yuling Yan |
| author_facet | Ting-Ruen Wei Senbao Lu Yuling Yan |
| author_sort | Ting-Ruen Wei |
| collection | DOAJ |
| description | An electrocardiography system records electrical activities of the heart, and it is used to assist doctors in the diagnosis of cardiac arrhythmia such as atrial fibrillation. This study presents a fast, automated deep-learning algorithm that predicts atrial fibrillation with excellent performance (F-1 score 88.2% and accuracy 97.3%). Our approach involves the pre-processing of ECG signals, followed by an alternative representation of the signals using a spectrogram, which is then fed to a fine-tuned EfficientNet B0, a pre-trained convolution neural network model, for the classification task. Using the transfer learning approach and with fine-tuning of the EfficientNet, we optimize the model to achieve highly efficient and effective classification of the atrial fibrillation. |
| first_indexed | 2024-03-09T20:41:57Z |
| format | Article |
| id | doaj.art-8a84c13b6670413381019930b0960a2d |
| institution | Directory Open Access Journal |
| issn | 2306-5354 |
| language | English |
| last_indexed | 2024-03-09T20:41:57Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Bioengineering |
| spelling | doaj.art-8a84c13b6670413381019930b0960a2d2023-11-23T22:57:18ZengMDPI AGBioengineering2306-53542022-10-0191052310.3390/bioengineering9100523Automated Atrial Fibrillation Detection with ECGTing-Ruen Wei0Senbao Lu1Yuling Yan2School of Engineering, Santa Clara University, Santa Clara, CA 95053, USASchool of Engineering, Santa Clara University, Santa Clara, CA 95053, USASchool of Engineering, Santa Clara University, Santa Clara, CA 95053, USAAn electrocardiography system records electrical activities of the heart, and it is used to assist doctors in the diagnosis of cardiac arrhythmia such as atrial fibrillation. This study presents a fast, automated deep-learning algorithm that predicts atrial fibrillation with excellent performance (F-1 score 88.2% and accuracy 97.3%). Our approach involves the pre-processing of ECG signals, followed by an alternative representation of the signals using a spectrogram, which is then fed to a fine-tuned EfficientNet B0, a pre-trained convolution neural network model, for the classification task. Using the transfer learning approach and with fine-tuning of the EfficientNet, we optimize the model to achieve highly efficient and effective classification of the atrial fibrillation.https://www.mdpi.com/2306-5354/9/10/523ECGA-fib detectiontransfer learning |
| spellingShingle | Ting-Ruen Wei Senbao Lu Yuling Yan Automated Atrial Fibrillation Detection with ECG Bioengineering ECG A-fib detection transfer learning |
| title | Automated Atrial Fibrillation Detection with ECG |
| title_full | Automated Atrial Fibrillation Detection with ECG |
| title_fullStr | Automated Atrial Fibrillation Detection with ECG |
| title_full_unstemmed | Automated Atrial Fibrillation Detection with ECG |
| title_short | Automated Atrial Fibrillation Detection with ECG |
| title_sort | automated atrial fibrillation detection with ecg |
| topic | ECG A-fib detection transfer learning |
| url | https://www.mdpi.com/2306-5354/9/10/523 |
| work_keys_str_mv | AT tingruenwei automatedatrialfibrillationdetectionwithecg AT senbaolu automatedatrialfibrillationdetectionwithecg AT yulingyan automatedatrialfibrillationdetectionwithecg |