Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding
Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large num...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Biosensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-6374/11/11/453 |
| _version_ | 1827677193651617792 |
|---|---|
| author | Yang Liu Qince Li Kuanquan Wang Jun Liu Runnan He Yongfeng Yuan Henggui Zhang |
| author_facet | Yang Liu Qince Li Kuanquan Wang Jun Liu Runnan He Yongfeng Yuan Henggui Zhang |
| author_sort | Yang Liu |
| collection | DOAJ |
| description | Automatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large number of possible label combinations and the imbalance among categories. Furthermore, the task of multi-label ECG classification is cost-sensitive, a fact that has usually been ignored in previous studies on the development of the model. To address these problems, in this work, we propose a novel deep learning model–based learning framework and a thresholding method, namely category imbalance and cost-sensitive thresholding (CICST), to incorporate prior knowledge about classification costs and the characteristic of category imbalance in designing a multi-label ECG classifier. The learning framework combines a residual convolutional network with a class-wise attention mechanism. We evaluate our method with a cost-sensitive metric on multiple realistic datasets. The results show that CICST achieved a cost-sensitive metric score of 0.641 ± 0.009 in a 5-fold cross-validation, outperforming other commonly used thresholding methods, including rank-based thresholding, proportion-based thresholding, and fixed thresholding. This demonstrates that, by taking into account the category imbalance and predefined cost information, our approach is effective in improving the performance and practicability of multi-label ECG classification models. |
| first_indexed | 2024-03-10T05:40:41Z |
| format | Article |
| id | doaj.art-d25e8d8ab59343f6be14ec1b9c762813 |
| institution | Directory Open Access Journal |
| issn | 2079-6374 |
| language | English |
| last_indexed | 2024-03-10T05:40:41Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Biosensors |
| spelling | doaj.art-d25e8d8ab59343f6be14ec1b9c7628132023-11-22T22:36:23ZengMDPI AGBiosensors2079-63742021-11-01111145310.3390/bios11110453Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive ThresholdingYang Liu0Qince Li1Kuanquan Wang2Jun Liu3Runnan He4Yongfeng Yuan5Henggui Zhang6School of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaPeng Cheng Laboratory, Shenzhen 518000, ChinaSchool of Computer Science and Technology, Harbin Institute of Technology, Harbin 150001, ChinaPeng Cheng Laboratory, Shenzhen 518000, ChinaAutomatic electrocardiogram (ECG) classification is a promising technology for the early screening and follow-up management of cardiovascular diseases. It is, by nature, a multi-label classification task owing to the coexistence of different kinds of diseases, and is challenging due to the large number of possible label combinations and the imbalance among categories. Furthermore, the task of multi-label ECG classification is cost-sensitive, a fact that has usually been ignored in previous studies on the development of the model. To address these problems, in this work, we propose a novel deep learning model–based learning framework and a thresholding method, namely category imbalance and cost-sensitive thresholding (CICST), to incorporate prior knowledge about classification costs and the characteristic of category imbalance in designing a multi-label ECG classifier. The learning framework combines a residual convolutional network with a class-wise attention mechanism. We evaluate our method with a cost-sensitive metric on multiple realistic datasets. The results show that CICST achieved a cost-sensitive metric score of 0.641 ± 0.009 in a 5-fold cross-validation, outperforming other commonly used thresholding methods, including rank-based thresholding, proportion-based thresholding, and fixed thresholding. This demonstrates that, by taking into account the category imbalance and predefined cost information, our approach is effective in improving the performance and practicability of multi-label ECG classification models.https://www.mdpi.com/2079-6374/11/11/453electrocardiogrammulti-label classificationdeep neural networkcategory correlationscategory imbalance |
| spellingShingle | Yang Liu Qince Li Kuanquan Wang Jun Liu Runnan He Yongfeng Yuan Henggui Zhang Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding Biosensors electrocardiogram multi-label classification deep neural network category correlations category imbalance |
| title | Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding |
| title_full | Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding |
| title_fullStr | Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding |
| title_full_unstemmed | Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding |
| title_short | Automatic Multi-Label ECG Classification with Category Imbalance and Cost-Sensitive Thresholding |
| title_sort | automatic multi label ecg classification with category imbalance and cost sensitive thresholding |
| topic | electrocardiogram multi-label classification deep neural network category correlations category imbalance |
| url | https://www.mdpi.com/2079-6374/11/11/453 |
| work_keys_str_mv | AT yangliu automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT qinceli automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT kuanquanwang automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT junliu automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT runnanhe automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT yongfengyuan automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding AT hengguizhang automaticmultilabelecgclassificationwithcategoryimbalanceandcostsensitivethresholding |