Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest
The automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1099-4300/21/3/305 |
| _version_ | 1817988980594966528 |
|---|---|
| author | Andoni Elola Elisabete Aramendi Unai Irusta Artzai Picón Erik Alonso Pamela Owens Ahamed Idris |
| author_facet | Andoni Elola Elisabete Aramendi Unai Irusta Artzai Picón Erik Alonso Pamela Owens Ahamed Idris |
| author_sort | Andoni Elola |
| collection | DOAJ |
| description | The automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse is the electrocardiogram (ECG). In this study we propose two deep neural network (DNN) architectures to detect pulse using short ECG segments (5 s), i.e., to classify the rhythm into pulseless electrical activity (PEA) or pulse-generating rhythm (PR). A total of 3914 5-s ECG segments, 2372 PR and 1542 PEA, were extracted from 279 OHCA episodes. Data were partitioned patient-wise into training (80%) and test (20%) sets. The first DNN architecture was a fully convolutional neural network, and the second architecture added a recurrent layer to learn temporal dependencies. Both DNN architectures were tuned using Bayesian optimization, and the results for the test set were compared to state-of-the art PR/PEA discrimination algorithms based on machine learning and hand crafted features. The PR/PEA classifiers were evaluated in terms of sensitivity (Se) for PR, specificity (Sp) for PEA, and the balanced accuracy (BAC), the average of Se and Sp. The Se/Sp/BAC of the DNN architectures were 94.1%/92.9%/93.5% for the first one, and 95.5%/91.6%/93.5% for the second one. Both architectures improved the performance of state of the art methods by more than 1.5 points in BAC. |
| first_indexed | 2024-04-14T00:41:38Z |
| format | Article |
| id | doaj.art-9741f226a3d74b929255cb9389c6f551 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-14T00:41:38Z |
| publishDate | 2019-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-9741f226a3d74b929255cb9389c6f5512022-12-22T02:22:10ZengMDPI AGEntropy1099-43002019-03-0121330510.3390/e21030305e21030305Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac ArrestAndoni Elola0Elisabete Aramendi1Unai Irusta2Artzai Picón3Erik Alonso4Pamela Owens5Ahamed Idris6Department of Communications Engineering, University of the Basque Country, 48013 Bilbao, SpainDepartment of Communications Engineering, University of the Basque Country, 48013 Bilbao, SpainDepartment of Communications Engineering, University of the Basque Country, 48013 Bilbao, SpainComputer Vision, TECNALIA Research & Innovation, 48160 Derio, SpainDepartment of Applied Mathematics, University of the Basque Country, 48013 Bilbao, SpainDepartment of Emergency Medicine, University of Texas Southwestern Medical Center, Dallas, TX 75390, USADepartment of Emergency Medicine, University of Texas Southwestern Medical Center, Dallas, TX 75390, USAThe automatic detection of pulse during out-of-hospital cardiac arrest (OHCA) is necessary for the early recognition of the arrest and the detection of return of spontaneous circulation (end of the arrest). The only signal available in every single defibrillator and valid for the detection of pulse is the electrocardiogram (ECG). In this study we propose two deep neural network (DNN) architectures to detect pulse using short ECG segments (5 s), i.e., to classify the rhythm into pulseless electrical activity (PEA) or pulse-generating rhythm (PR). A total of 3914 5-s ECG segments, 2372 PR and 1542 PEA, were extracted from 279 OHCA episodes. Data were partitioned patient-wise into training (80%) and test (20%) sets. The first DNN architecture was a fully convolutional neural network, and the second architecture added a recurrent layer to learn temporal dependencies. Both DNN architectures were tuned using Bayesian optimization, and the results for the test set were compared to state-of-the art PR/PEA discrimination algorithms based on machine learning and hand crafted features. The PR/PEA classifiers were evaluated in terms of sensitivity (Se) for PR, specificity (Sp) for PEA, and the balanced accuracy (BAC), the average of Se and Sp. The Se/Sp/BAC of the DNN architectures were 94.1%/92.9%/93.5% for the first one, and 95.5%/91.6%/93.5% for the second one. Both architectures improved the performance of state of the art methods by more than 1.5 points in BAC.https://www.mdpi.com/1099-4300/21/3/305pulse detectionECGpulseless electrical activityout-of-hospital cardiac arrestconvolutional neural networkdeep learningBayesian optimization |
| spellingShingle | Andoni Elola Elisabete Aramendi Unai Irusta Artzai Picón Erik Alonso Pamela Owens Ahamed Idris Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest Entropy pulse detection ECG pulseless electrical activity out-of-hospital cardiac arrest convolutional neural network deep learning Bayesian optimization |
| title | Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest |
| title_full | Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest |
| title_fullStr | Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest |
| title_full_unstemmed | Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest |
| title_short | Deep Neural Networks for ECG-Based Pulse Detection during Out-of-Hospital Cardiac Arrest |
| title_sort | deep neural networks for ecg based pulse detection during out of hospital cardiac arrest |
| topic | pulse detection ECG pulseless electrical activity out-of-hospital cardiac arrest convolutional neural network deep learning Bayesian optimization |
| url | https://www.mdpi.com/1099-4300/21/3/305 |
| work_keys_str_mv | AT andonielola deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT elisabetearamendi deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT unaiirusta deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT artzaipicon deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT erikalonso deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT pamelaowens deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest AT ahamedidris deepneuralnetworksforecgbasedpulsedetectionduringoutofhospitalcardiacarrest |