Publication Details |
| Category | Text Publication |
| Reference Category | Journals |
| DOI | 10.1088/1361-6579/ac77d1 |
| Document | accepted manuscript |
| Title (Primary) | Arrhythmia classification of 12-lead and reduced-lead electrocardiograms via recurrent networks, scattering, and phase harmonic correlation |
| Author | Warrick, P.A.; Lostanlen, V.; Eickenberg, M.; Homsi, M.N.; Rodríguez, A.C.; Andén, J. |
| Source Titel | Physiological Measurement |
| Year | 2022 |
| Department | MOLSYB |
| Volume | 43 |
| Issue | 9 |
| Page From | art. 094002 |
| Language | englisch |
| Topic | T9 Healthy Planet |
| Keywords | electrocardiography; scattering transform; phase harmonic correlation; canonical correlation analysis; convolutional neural networks; long short-term memory networks |
| Abstract | We describe an automatic classifier of arrhythmias based on 12-lead and reduced-lead electrocardiograms. Our classifier comprises four modules: scattering transform (ST), phase harmonic correlation (PHC), depthwise separable convolutions (DSC), and a long short-term memory (LSTM) network. It is trained on PhysioNet/Computing in Cardiology Challenge 2021 data. The ST captures short-term temporal ECG modulations while the PHC characterizes the phase dependence of coherent ECG components. Both reduce the sampling rate to a few samples per typical heart beat. We pass the output of the ST and PHC to a depthwise-separable convolution layer (DSC) which combines lead responses separately for each ST or PHC coefficient and then combines resulting values across all coefficients. At a deeper level, two LSTM layers integrate local variations of the input over long time scales. We train in an end-to-end fashion as a multilabel classification problem with a normal and 25 arrhythmia classes. Lastly, we use canonical correlation analysis (CCA) for transfer learning from 12-lead ST and PHC representations to reduced-lead ones. After local cross-validation on the public data from the challenge, our team 'BitScattered' achieved the following results: 0.682 ± 0.0095 for 12-lead; 0.666 ± 0.0257 for 6-lead; 0.674 ± 0.0185 for 4-lead; 0.661 ± 0.0098 for 3-lead; and 0.662 ± 0.0151 for 2-lead. |
| Persistent UFZ Identifier | https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=26615 |
| Warrick, P.A., Lostanlen, V., Eickenberg, M., Homsi, M.N., Rodríguez, A.C., Andén, J. (2022): Arrhythmia classification of 12-lead and reduced-lead electrocardiograms via recurrent networks, scattering, and phase harmonic correlation Physiol. Meas. 43 (9), art. 094002 10.1088/1361-6579/ac77d1 |
|