A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet
Cardiovascular disease (CVD) has become one of the most serious diseases that threaten human health. Over the past decades, over 150 million humans have died of CVDs. Hence, timely prediction of CVDs is especially important. Currently, deep learning algorithm-based CVD diagnosis methods are extensiv...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/14/3214 |
| _version_ | 1818001016317018112 |
|---|---|
| author | Weiyi Yang Yujuan Si Di Wang Gong Zhang |
| author_facet | Weiyi Yang Yujuan Si Di Wang Gong Zhang |
| author_sort | Weiyi Yang |
| collection | DOAJ |
| description | Cardiovascular disease (CVD) has become one of the most serious diseases that threaten human health. Over the past decades, over 150 million humans have died of CVDs. Hence, timely prediction of CVDs is especially important. Currently, deep learning algorithm-based CVD diagnosis methods are extensively employed, however, most such algorithms can only utilize one-lead ECGs. Hence, the potential information in other-lead ECGs was not utilized. To address this issue, we have developed novel methods for diagnosing arrhythmia. In this work, DL-CCANet and TL-CCANet are proposed to extract abstract discriminating features from dual-lead and three-lead ECGs, respectively. Then, the linear support vector machine specializing in high-dimensional features is used as the classifier model. On the MIT-BIH database, a 95.2% overall accuracy is obtained by detecting 15 types of heartbeats using DL-CCANet. On the INCART database, overall accuracies of 94.01% (II and V1 leads), 93.90% (V1 and V5 leads) and 94.07% (II and V5 leads) are achieved by detecting seven types of heartbeat using DL-CCANet, while TL-CCANet yields a higher overall accuracy of 95.52% using the above three leads. In addition, all of the above experiments are implemented using noisy ECG data. The proposed methods have potential to be applied in the clinic and mobile devices. |
| first_indexed | 2024-04-14T03:28:55Z |
| format | Article |
| id | doaj.art-412f78e21fea401585b732aa57e6c369 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T03:28:55Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-412f78e21fea401585b732aa57e6c3692022-12-22T02:15:02ZengMDPI AGSensors1424-82202019-07-011914321410.3390/s19143214s19143214A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANetWeiyi Yang0Yujuan Si1Di Wang2Gong Zhang3College of Communication Engineering, Jilin University, Changchun 130012, ChinaCollege of Communication Engineering, Jilin University, Changchun 130012, ChinaCollege of Communication Engineering, Jilin University, Changchun 130012, ChinaCollege of Communication Engineering, Jilin University, Changchun 130012, ChinaCardiovascular disease (CVD) has become one of the most serious diseases that threaten human health. Over the past decades, over 150 million humans have died of CVDs. Hence, timely prediction of CVDs is especially important. Currently, deep learning algorithm-based CVD diagnosis methods are extensively employed, however, most such algorithms can only utilize one-lead ECGs. Hence, the potential information in other-lead ECGs was not utilized. To address this issue, we have developed novel methods for diagnosing arrhythmia. In this work, DL-CCANet and TL-CCANet are proposed to extract abstract discriminating features from dual-lead and three-lead ECGs, respectively. Then, the linear support vector machine specializing in high-dimensional features is used as the classifier model. On the MIT-BIH database, a 95.2% overall accuracy is obtained by detecting 15 types of heartbeats using DL-CCANet. On the INCART database, overall accuracies of 94.01% (II and V1 leads), 93.90% (V1 and V5 leads) and 94.07% (II and V5 leads) are achieved by detecting seven types of heartbeat using DL-CCANet, while TL-CCANet yields a higher overall accuracy of 95.52% using the above three leads. In addition, all of the above experiments are implemented using noisy ECG data. The proposed methods have potential to be applied in the clinic and mobile devices.https://www.mdpi.com/1424-8220/19/14/3214arrhythmia diagnosisCCANetmuti-lead ECG classificationlinear support vector machineMIT-BIH databaseINCART database |
| spellingShingle | Weiyi Yang Yujuan Si Di Wang Gong Zhang A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet Sensors arrhythmia diagnosis CCANet muti-lead ECG classification linear support vector machine MIT-BIH database INCART database |
| title | A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet |
| title_full | A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet |
| title_fullStr | A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet |
| title_full_unstemmed | A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet |
| title_short | A Novel Approach for Multi-Lead ECG Classification Using DL-CCANet and TL-CCANet |
| title_sort | novel approach for multi lead ecg classification using dl ccanet and tl ccanet |
| topic | arrhythmia diagnosis CCANet muti-lead ECG classification linear support vector machine MIT-BIH database INCART database |
| url | https://www.mdpi.com/1424-8220/19/14/3214 |
| work_keys_str_mv | AT weiyiyang anovelapproachformultileadecgclassificationusingdlccanetandtlccanet AT yujuansi anovelapproachformultileadecgclassificationusingdlccanetandtlccanet AT diwang anovelapproachformultileadecgclassificationusingdlccanetandtlccanet AT gongzhang anovelapproachformultileadecgclassificationusingdlccanetandtlccanet AT weiyiyang novelapproachformultileadecgclassificationusingdlccanetandtlccanet AT yujuansi novelapproachformultileadecgclassificationusingdlccanetandtlccanet AT diwang novelapproachformultileadecgclassificationusingdlccanetandtlccanet AT gongzhang novelapproachformultileadecgclassificationusingdlccanetandtlccanet |