Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model
Background and Objectives: Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Journal of Personalized Medicine |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4426/13/5/820 |
| _version_ | 1797599464496562176 |
|---|---|
| author | Yating Hu Tengfei Feng Miao Wang Chengyu Liu Hong Tang |
| author_facet | Yating Hu Tengfei Feng Miao Wang Chengyu Liu Hong Tang |
| author_sort | Yating Hu |
| collection | DOAJ |
| description | Background and Objectives: Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a challenge due to its intermittence and unpredictability. A method for the accurate detection of AF is still needed. Methods: A deep learning model was used to detect atrial fibrillation. Here, a distinction was not made between AF and atrial flutter (AFL), both of which manifest as a similar pattern on an electrocardiogram (ECG). This method not only discriminated AF from normal rhythm of the heart, but also detected its onset and offset. The proposed model involved residual blocks and a Transformer encoder. Results and Conclusions: The data used for training were obtained from the CPSC2021 Challenge, and were collected using dynamic ECG devices. Tests on four public datasets validated the availability of the proposed method. The best performance for AF rhythm testing attained an accuracy of 98.67%, a sensitivity of 87.69%, and a specificity of 98.56%. In onset and offset detection, it obtained a sensitivity of 95.90% and 87.70%, respectively. The algorithm with a low FPR of 0.46% was able to reduce troubling false alarms. The model had a great capability to discriminate AF from normal rhythm and to detect its onset and offset. Noise stress tests were conducted after mixing three types of noise. We visualized the model’s features using a heatmap and illustrated its interpretability. The model focused directly on the crucial ECG waveform where showed obvious characteristics of AF. |
| first_indexed | 2024-03-11T03:35:48Z |
| format | Article |
| id | doaj.art-ba80d6f8bb3f4c5bbf8043a31b37205c |
| institution | Directory Open Access Journal |
| issn | 2075-4426 |
| language | English |
| last_indexed | 2024-03-11T03:35:48Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Personalized Medicine |
| spelling | doaj.art-ba80d6f8bb3f4c5bbf8043a31b37205c2023-11-18T02:04:36ZengMDPI AGJournal of Personalized Medicine2075-44262023-05-0113582010.3390/jpm13050820Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning ModelYating Hu0Tengfei Feng1Miao Wang2Chengyu Liu3Hong Tang4School of Biomedical Engineering, Dalian University of Technology, Dalian 116024, ChinaDepartment of Psychiatry, Psychotherapy and Psychosomatics, Medical School, RWTH Aachen University, 52074 Aachen, GermanySchool of Biomedical Engineering, Dalian University of Technology, Dalian 116024, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Biomedical Engineering, Dalian University of Technology, Dalian 116024, ChinaBackground and Objectives: Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a challenge due to its intermittence and unpredictability. A method for the accurate detection of AF is still needed. Methods: A deep learning model was used to detect atrial fibrillation. Here, a distinction was not made between AF and atrial flutter (AFL), both of which manifest as a similar pattern on an electrocardiogram (ECG). This method not only discriminated AF from normal rhythm of the heart, but also detected its onset and offset. The proposed model involved residual blocks and a Transformer encoder. Results and Conclusions: The data used for training were obtained from the CPSC2021 Challenge, and were collected using dynamic ECG devices. Tests on four public datasets validated the availability of the proposed method. The best performance for AF rhythm testing attained an accuracy of 98.67%, a sensitivity of 87.69%, and a specificity of 98.56%. In onset and offset detection, it obtained a sensitivity of 95.90% and 87.70%, respectively. The algorithm with a low FPR of 0.46% was able to reduce troubling false alarms. The model had a great capability to discriminate AF from normal rhythm and to detect its onset and offset. Noise stress tests were conducted after mixing three types of noise. We visualized the model’s features using a heatmap and illustrated its interpretability. The model focused directly on the crucial ECG waveform where showed obvious characteristics of AF.https://www.mdpi.com/2075-4426/13/5/820atrial fibrillationelectrocardiogramdeep learningTransformer |
| spellingShingle | Yating Hu Tengfei Feng Miao Wang Chengyu Liu Hong Tang Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model Journal of Personalized Medicine atrial fibrillation electrocardiogram deep learning Transformer |
| title | Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model |
| title_full | Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model |
| title_fullStr | Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model |
| title_full_unstemmed | Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model |
| title_short | Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model |
| title_sort | detection of paroxysmal atrial fibrillation from dynamic ecg recordings based on a deep learning model |
| topic | atrial fibrillation electrocardiogram deep learning Transformer |
| url | https://www.mdpi.com/2075-4426/13/5/820 |
| work_keys_str_mv | AT yatinghu detectionofparoxysmalatrialfibrillationfromdynamicecgrecordingsbasedonadeeplearningmodel AT tengfeifeng detectionofparoxysmalatrialfibrillationfromdynamicecgrecordingsbasedonadeeplearningmodel AT miaowang detectionofparoxysmalatrialfibrillationfromdynamicecgrecordingsbasedonadeeplearningmodel AT chengyuliu detectionofparoxysmalatrialfibrillationfromdynamicecgrecordingsbasedonadeeplearningmodel AT hongtang detectionofparoxysmalatrialfibrillationfromdynamicecgrecordingsbasedonadeeplearningmodel |