Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model
IntroductionThe risk of mortality associated with cardiac arrhythmias is considerable, and their diagnosis presents significant challenges, often resulting in misdiagnosis. This situation highlights the necessity for an automated, efficient, and real-time detection method aimed at enhancing diagnost...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-01-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2024.1473482/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558657590886400 |
|---|---|
| author | Youfu He Youfu He Youfu He Yu Zhou Yu Zhou Yu Qian Jingjie Liu Jinyan Zhang Debin Liu Qiang Wu Qiang Wu |
| author_facet | Youfu He Youfu He Youfu He Yu Zhou Yu Zhou Yu Qian Jingjie Liu Jinyan Zhang Debin Liu Qiang Wu Qiang Wu |
| author_sort | Youfu He |
| collection | DOAJ |
| description | IntroductionThe risk of mortality associated with cardiac arrhythmias is considerable, and their diagnosis presents significant challenges, often resulting in misdiagnosis. This situation highlights the necessity for an automated, efficient, and real-time detection method aimed at enhancing diagnostic accuracy and improving patient outcomes.MethodsThe present study is centered on the development of a portable deep learning model for the detection of arrhythmias via electrocardiogram (ECG) signals, referred to as CardioAttentionNet (CANet). CANet integrates Bi-directional Long Short-Term Memory (BiLSTM) networks, Multi-head Attention mechanisms, and Depthwise Separable Convolution, thereby facilitating its application in portable devices for early diagnosis. The architecture of CANet allows for effective processing of extended ECG patterns and detailed feature extraction without a substantial increase in model size.ResultsEmpirical results indicate that CANet outperformed traditional models in terms of predictive performance and stability, as confirmed by comprehensive cross-validation. The model demonstrated exceptional capabilities in detecting cardiac arrhythmias, surpassing existing models in both cross-validation and external testing scenarios. Specifically, CANet achieved high accuracy in classifying various arrhythmic events, with the following accuracies reported for different categories: Normal (97.37 ± 0.30%), Supraventricular (98.09 ± 0.25%), Ventricular (92.92 ± 0.09%), Atrial Fibrillation (99.07 ± 0.13%), and Unclassified arrhythmias (99.68 ± 0.06%). In external evaluations, CANet attained an average accuracy of 94.41%, with the area under the curve (AUC) for each category exceeding 99%, thereby demonstrating its substantial clinical applicability and significant advancements over traditional models.DiscussionThe deep learning model proposed in this study has the potential to enhance the accuracy of early diagnosis for various types of arrhythmias. Looking ahead, this technology is anticipated to provide improved medical services for patients with heart disease through continuous, non-invasive monitoring and timely intervention. |
| format | Article |
| id | doaj-art-d58f6551500c4b7fac0dda8aed02dfa4 |
| institution | Kabale University |
| issn | 2297-055X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj-art-d58f6551500c4b7fac0dda8aed02dfa42025-01-06T06:59:39ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2025-01-011110.3389/fcvm.2024.14734821473482Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning modelYoufu He0Youfu He1Youfu He2Yu Zhou3Yu Zhou4Yu Qian5Jingjie Liu6Jinyan Zhang7Debin Liu8Qiang Wu9Qiang Wu10Medical College, Guizhou University, Guiyang, Guizhou, ChinaDepartment of Cardiology, Guizhou Provincial People’s Hospital, Guiyang, Guizhou, ChinaDepartment of Cardiology, Guizhou Provincial Cardiovascular Disease Clinical Medicine Research Center, Guiyang, Guizhou, ChinaDepartment of Cardiology, Guizhou Provincial People’s Hospital, Guiyang, Guizhou, ChinaDepartment of Cardiology, Guizhou Provincial Cardiovascular Disease Clinical Medicine Research Center, Guiyang, Guizhou, ChinaDepartment of Cardiology, The Second Affiliated Hospital of Zunyi Medical University, Zunyi, Guizhou, ChinaDepartment of Cardiology, First Affiliated Hospital of Dalian Medical University, Liaoyang, Liaoning, ChinaSchool of Life Science and Technology, University of Electronic Science and Technology of China, Chengdu, Sichuan, ChinaDepartment of Cardiology, The Second People’s Hospital of Shantou, Shantou, Guangdong, ChinaDepartment of Cardiology, Guizhou Provincial People’s Hospital, Guiyang, Guizhou, ChinaDepartment of Cardiology, Guizhou Provincial Cardiovascular Disease Clinical Medicine Research Center, Guiyang, Guizhou, ChinaIntroductionThe risk of mortality associated with cardiac arrhythmias is considerable, and their diagnosis presents significant challenges, often resulting in misdiagnosis. This situation highlights the necessity for an automated, efficient, and real-time detection method aimed at enhancing diagnostic accuracy and improving patient outcomes.MethodsThe present study is centered on the development of a portable deep learning model for the detection of arrhythmias via electrocardiogram (ECG) signals, referred to as CardioAttentionNet (CANet). CANet integrates Bi-directional Long Short-Term Memory (BiLSTM) networks, Multi-head Attention mechanisms, and Depthwise Separable Convolution, thereby facilitating its application in portable devices for early diagnosis. The architecture of CANet allows for effective processing of extended ECG patterns and detailed feature extraction without a substantial increase in model size.ResultsEmpirical results indicate that CANet outperformed traditional models in terms of predictive performance and stability, as confirmed by comprehensive cross-validation. The model demonstrated exceptional capabilities in detecting cardiac arrhythmias, surpassing existing models in both cross-validation and external testing scenarios. Specifically, CANet achieved high accuracy in classifying various arrhythmic events, with the following accuracies reported for different categories: Normal (97.37 ± 0.30%), Supraventricular (98.09 ± 0.25%), Ventricular (92.92 ± 0.09%), Atrial Fibrillation (99.07 ± 0.13%), and Unclassified arrhythmias (99.68 ± 0.06%). In external evaluations, CANet attained an average accuracy of 94.41%, with the area under the curve (AUC) for each category exceeding 99%, thereby demonstrating its substantial clinical applicability and significant advancements over traditional models.DiscussionThe deep learning model proposed in this study has the potential to enhance the accuracy of early diagnosis for various types of arrhythmias. Looking ahead, this technology is anticipated to provide improved medical services for patients with heart disease through continuous, non-invasive monitoring and timely intervention.https://www.frontiersin.org/articles/10.3389/fcvm.2024.1473482/fullcardiac arrhythmiaselectrocardiogramportable deep learning modeltransformer modelLong Short-Term MemoryMobileNet |
| spellingShingle | Youfu He Youfu He Youfu He Yu Zhou Yu Zhou Yu Qian Jingjie Liu Jinyan Zhang Debin Liu Qiang Wu Qiang Wu Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model Frontiers in Cardiovascular Medicine cardiac arrhythmias electrocardiogram portable deep learning model transformer model Long Short-Term Memory MobileNet |
| title | Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model |
| title_full | Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model |
| title_fullStr | Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model |
| title_full_unstemmed | Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model |
| title_short | Cardioattentionnet: advancing ECG beat characterization with a high-accuracy and portable deep learning model |
| title_sort | cardioattentionnet advancing ecg beat characterization with a high accuracy and portable deep learning model |
| topic | cardiac arrhythmias electrocardiogram portable deep learning model transformer model Long Short-Term Memory MobileNet |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2024.1473482/full |
| work_keys_str_mv | AT youfuhe cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT youfuhe cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT youfuhe cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT yuzhou cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT yuzhou cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT yuqian cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT jingjieliu cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT jinyanzhang cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT debinliu cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT qiangwu cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel AT qiangwu cardioattentionnetadvancingecgbeatcharacterizationwithahighaccuracyandportabledeeplearningmodel |