Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks
Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using con...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/22/6/595 |
| _version_ | 1797566867725877248 |
|---|---|
| author | Iraia Isasi Unai Irusta Elisabete Aramendi Trygve Eftestøl Jo Kramer-Johansen Lars Wik |
| author_facet | Iraia Isasi Unai Irusta Elisabete Aramendi Trygve Eftestøl Jo Kramer-Johansen Lars Wik |
| author_sort | Iraia Isasi |
| collection | DOAJ |
| description | Chest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9 <inline-formula> <math display="inline"> <semantics> <mi mathvariant="normal">s</mi> </semantics> </math> </inline-formula> extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock/no-shock classification. A 5-fold cross validation architecture was adopted to train/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6–96.8), 96.1% (95.8–96.5), 96.1% (95.7–96.4) and 96.0% (95.5–96.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy. |
| first_indexed | 2024-03-10T19:33:29Z |
| format | Article |
| id | doaj.art-32d8805c11794e5fa75c3b79a507212e |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-03-10T19:33:29Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-32d8805c11794e5fa75c3b79a507212e2023-11-20T01:56:13ZengMDPI AGEntropy1099-43002020-05-0122659510.3390/e22060595Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural NetworksIraia Isasi0Unai Irusta1Elisabete Aramendi2Trygve Eftestøl3Jo Kramer-Johansen4Lars Wik5Department of Communications Engineering, University of the Basque Country UPV/EHU, 48013 Bilbao, SpainDepartment of Communications Engineering, University of the Basque Country UPV/EHU, 48013 Bilbao, SpainDepartment of Communications Engineering, University of the Basque Country UPV/EHU, 48013 Bilbao, SpainDepartment of Electrical Engineering and Computer Science, University of Stavanger, 4036 Stavanger, NorwayNorwegian National Advisory Unit on Prehospital Emergency Medicine (NAKOS), Oslo University Hospital and University of Oslo, 0424 Oslo, NorwayNorwegian National Advisory Unit on Prehospital Emergency Medicine (NAKOS), Oslo University Hospital and University of Oslo, 0424 Oslo, NorwayChest compressions during cardiopulmonary resuscitation (CPR) induce artifacts in the ECG that may provoque inaccurate rhythm classification by the algorithm of the defibrillator. The objective of this study was to design an algorithm to produce reliable shock/no-shock decisions during CPR using convolutional neural networks (CNN). A total of 3319 ECG segments of 9 <inline-formula> <math display="inline"> <semantics> <mi mathvariant="normal">s</mi> </semantics> </math> </inline-formula> extracted during chest compressions were used, whereof 586 were shockable and 2733 nonshockable. Chest compression artifacts were removed using a Recursive Least Squares (RLS) filter, and the filtered ECG was fed to a CNN classifier with three convolutional blocks and two fully connected layers for the shock/no-shock classification. A 5-fold cross validation architecture was adopted to train/test the algorithm, and the proccess was repeated 100 times to statistically characterize the performance. The proposed architecture was compared to the most accurate algorithms that include handcrafted ECG features and a random forest classifier (baseline model). The median (90% confidence interval) sensitivity, specificity, accuracy and balanced accuracy of the method were 95.8% (94.6–96.8), 96.1% (95.8–96.5), 96.1% (95.7–96.4) and 96.0% (95.5–96.5), respectively. The proposed algorithm outperformed the baseline model by 0.6-points in accuracy. This new approach shows the potential of deep learning methods to provide reliable diagnosis of the cardiac rhythm without interrupting chest compression therapy.https://www.mdpi.com/1099-4300/22/6/595out-of-hospital cardiac arrest (OHCA)cardiopulmonary resuscitation (CPR)electrocardiogram (ECG)adaptive filterdeep learningmachine learning |
| spellingShingle | Iraia Isasi Unai Irusta Elisabete Aramendi Trygve Eftestøl Jo Kramer-Johansen Lars Wik Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks Entropy out-of-hospital cardiac arrest (OHCA) cardiopulmonary resuscitation (CPR) electrocardiogram (ECG) adaptive filter deep learning machine learning |
| title | Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks |
| title_full | Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks |
| title_fullStr | Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks |
| title_full_unstemmed | Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks |
| title_short | Rhythm Analysis during Cardiopulmonary Resuscitation Using Convolutional Neural Networks |
| title_sort | rhythm analysis during cardiopulmonary resuscitation using convolutional neural networks |
| topic | out-of-hospital cardiac arrest (OHCA) cardiopulmonary resuscitation (CPR) electrocardiogram (ECG) adaptive filter deep learning machine learning |
| url | https://www.mdpi.com/1099-4300/22/6/595 |
| work_keys_str_mv | AT iraiaisasi rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks AT unaiirusta rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks AT elisabetearamendi rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks AT trygveeftestøl rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks AT jokramerjohansen rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks AT larswik rhythmanalysisduringcardiopulmonaryresuscitationusingconvolutionalneuralnetworks |