A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings
Entropy-based atrial fibrillation (AF) detectors have been applied for short-term electrocardiogram (ECG) analysis. However, existing methods suffer from several limitations. To enhance the performance of entropy-based AF detectors, we have developed a new entropy measure, named Entropy<sub>AF...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-11-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/20/12/904 |
| _version_ | 1811303775905775616 |
|---|---|
| author | Lina Zhao Chengyu Liu Shoushui Wei Qin Shen Fan Zhou Jianqing Li |
| author_facet | Lina Zhao Chengyu Liu Shoushui Wei Qin Shen Fan Zhou Jianqing Li |
| author_sort | Lina Zhao |
| collection | DOAJ |
| description | Entropy-based atrial fibrillation (AF) detectors have been applied for short-term electrocardiogram (ECG) analysis. However, existing methods suffer from several limitations. To enhance the performance of entropy-based AF detectors, we have developed a new entropy measure, named Entropy<sub>AF</sub>, which includes the following improvements: (1) use of a ranged function rather than the Chebyshev function to define vector distance, (2) use of a fuzzy function to determine vector similarity, (3) replacement of the probability estimation with density estimation for entropy calculation, (4) use of a flexible distance threshold parameter, and (5) use of adjusted entropy results for the heart rate effect. Entropy<sub>AF</sub> was trained using the MIT-BIH Atrial Fibrillation (AF) database, and tested on the clinical wearable long-term AF recordings. Three previous entropy-based AF detectors were used for comparison: sample entropy (SampEn), fuzzy measure entropy (FuzzyMEn) and coefficient of sample entropy (COSEn). For classifying AF and non-AF rhythms in the MIT-BIH AF database, Entropy<sub>AF</sub> achieved the highest area under receiver operating characteristic curve (AUC) values of 98.15% when using a 30-beat time window, which was higher than COSEn with AUC of 91.86%. SampEn and FuzzyMEn resulted in much lower AUCs of 74.68% and 79.24% respectively. For classifying AF and non-AF rhythms in the clinical wearable AF database, Entropy<sub>AF</sub> also generated the largest values of Youden index (77.94%), sensitivity (92.77%), specificity (85.17%), accuracy (87.10%), positive predictivity (68.09%) and negative predictivity (97.18%). COSEn had the second-best accuracy of 78.63%, followed by an accuracy of 65.08% in FuzzyMEn and an accuracy of 59.91% in SampEn. The new proposed Entropy<sub>AF</sub> also generated highest classification accuracy when using a 12-beat time window. In addition, the results from time cost analysis verified the efficiency of the new Entropy<sub>AF</sub>. This study showed the better discrimination ability for identifying AF when using Entropy<sub>AF</sub> method, indicating that it would be useful for the practical clinical wearable AF scanning. |
| first_indexed | 2024-04-13T07:54:03Z |
| format | Article |
| id | doaj.art-d5568bb98c584ee1b893517a21f1947f |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-13T07:54:03Z |
| publishDate | 2018-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-d5568bb98c584ee1b893517a21f1947f2022-12-22T02:55:27ZengMDPI AGEntropy1099-43002018-11-01201290410.3390/e20120904e20120904A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG RecordingsLina Zhao0Chengyu Liu1Shoushui Wei2Qin Shen3Fan Zhou4Jianqing Li5School of Control Science and Engineering, Shandong University, Jinan 250061, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Control Science and Engineering, Shandong University, Jinan 250061, ChinaDepartment of Cardiovascular Medicine, First Affiliated Hospital of Nanjing Medical University, Nanjing 210036, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaSchool of Instrument Science and Engineering, Southeast University, Nanjing 210096, ChinaEntropy-based atrial fibrillation (AF) detectors have been applied for short-term electrocardiogram (ECG) analysis. However, existing methods suffer from several limitations. To enhance the performance of entropy-based AF detectors, we have developed a new entropy measure, named Entropy<sub>AF</sub>, which includes the following improvements: (1) use of a ranged function rather than the Chebyshev function to define vector distance, (2) use of a fuzzy function to determine vector similarity, (3) replacement of the probability estimation with density estimation for entropy calculation, (4) use of a flexible distance threshold parameter, and (5) use of adjusted entropy results for the heart rate effect. Entropy<sub>AF</sub> was trained using the MIT-BIH Atrial Fibrillation (AF) database, and tested on the clinical wearable long-term AF recordings. Three previous entropy-based AF detectors were used for comparison: sample entropy (SampEn), fuzzy measure entropy (FuzzyMEn) and coefficient of sample entropy (COSEn). For classifying AF and non-AF rhythms in the MIT-BIH AF database, Entropy<sub>AF</sub> achieved the highest area under receiver operating characteristic curve (AUC) values of 98.15% when using a 30-beat time window, which was higher than COSEn with AUC of 91.86%. SampEn and FuzzyMEn resulted in much lower AUCs of 74.68% and 79.24% respectively. For classifying AF and non-AF rhythms in the clinical wearable AF database, Entropy<sub>AF</sub> also generated the largest values of Youden index (77.94%), sensitivity (92.77%), specificity (85.17%), accuracy (87.10%), positive predictivity (68.09%) and negative predictivity (97.18%). COSEn had the second-best accuracy of 78.63%, followed by an accuracy of 65.08% in FuzzyMEn and an accuracy of 59.91% in SampEn. The new proposed Entropy<sub>AF</sub> also generated highest classification accuracy when using a 12-beat time window. In addition, the results from time cost analysis verified the efficiency of the new Entropy<sub>AF</sub>. This study showed the better discrimination ability for identifying AF when using Entropy<sub>AF</sub> method, indicating that it would be useful for the practical clinical wearable AF scanning.https://www.mdpi.com/1099-4300/20/12/904atrial fibrillation (AF)sample entropy (SampEn)fuzzy measure entropy (FuzzyMEn)coefficient of sample entropy (COSEn)wearable ECGRR time seriescardiac rhythm |
| spellingShingle | Lina Zhao Chengyu Liu Shoushui Wei Qin Shen Fan Zhou Jianqing Li A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings Entropy atrial fibrillation (AF) sample entropy (SampEn) fuzzy measure entropy (FuzzyMEn) coefficient of sample entropy (COSEn) wearable ECG RR time series cardiac rhythm |
| title | A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings |
| title_full | A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings |
| title_fullStr | A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings |
| title_full_unstemmed | A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings |
| title_short | A New Entropy-Based Atrial Fibrillation Detection Method for Scanning Wearable ECG Recordings |
| title_sort | new entropy based atrial fibrillation detection method for scanning wearable ecg recordings |
| topic | atrial fibrillation (AF) sample entropy (SampEn) fuzzy measure entropy (FuzzyMEn) coefficient of sample entropy (COSEn) wearable ECG RR time series cardiac rhythm |
| url | https://www.mdpi.com/1099-4300/20/12/904 |
| work_keys_str_mv | AT linazhao anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT chengyuliu anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT shoushuiwei anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT qinshen anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT fanzhou anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT jianqingli anewentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT linazhao newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT chengyuliu newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT shoushuiwei newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT qinshen newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT fanzhou newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings AT jianqingli newentropybasedatrialfibrillationdetectionmethodforscanningwearableecgrecordings |