TY - GEN
T1 - Deep Learning for Pulse Detection in Out-of-Hospital Cardiac Arrest Using the ECG
AU - Elola, Andoni
AU - Aramendi, Elisabete
AU - Irusta, Unai
AU - Picon, Artzai
AU - Alonso, Erik
AU - Owens, Pamela
AU - Idris, Ahamed
N1 - Funding Information:
This work has been partially supported by the Spanish Ministerio de Economía y Competitividad, jointly with the Fondo Europeo de Desarrollo Regional (FEDER), through project TEC2015-64678-R, by the University of the Basque Country via the Ayudas a Grupos de Inves-tigación GIU17/031 and the unit UFI11/16, and by the Basque Government through the grant PRE 2017 1 0112.
Publisher Copyright:
© 2018 Creative Commons Attribution.
PY - 2018/9
Y1 - 2018/9
N2 - Pulse detection during out-of-hospital cardiac arrest is necessary to identify cardiac arrest and detect return of spontaneous circulation. Currently, carotid pulse checking and checking for signs of life are the most widespread procedures for pulse detection, but both have been proven inaccurate and time consuming. Automatic methods that could be integrated in Automated External Defibrillators (AEDs) are needed. In this study we propose a deep neural network classifier to detect pulse using exclusively the ECG. We extracted 3914 segments of 4s from 279 patients, all of them with an organized rhythm. They were annotated as pulsed rhythm or pulseless rhythm based on clinical information. A total of 2372 pulsed rhythms and 1542 pulseless rhythms were included in the study. To train and test the model 3038 (223 patients) and 876 segments (56 patients) were used, respectively. The model was evaluated in terms of Sensitivity (Se) and Specificity (Sp) for pulse detection. The network showed a Se/Sp of 89.4%/97.2% during training process and 91.7%/92.5% for the test set.
AB - Pulse detection during out-of-hospital cardiac arrest is necessary to identify cardiac arrest and detect return of spontaneous circulation. Currently, carotid pulse checking and checking for signs of life are the most widespread procedures for pulse detection, but both have been proven inaccurate and time consuming. Automatic methods that could be integrated in Automated External Defibrillators (AEDs) are needed. In this study we propose a deep neural network classifier to detect pulse using exclusively the ECG. We extracted 3914 segments of 4s from 279 patients, all of them with an organized rhythm. They were annotated as pulsed rhythm or pulseless rhythm based on clinical information. A total of 2372 pulsed rhythms and 1542 pulseless rhythms were included in the study. To train and test the model 3038 (223 patients) and 876 segments (56 patients) were used, respectively. The model was evaluated in terms of Sensitivity (Se) and Specificity (Sp) for pulse detection. The network showed a Se/Sp of 89.4%/97.2% during training process and 91.7%/92.5% for the test set.
UR - http://www.scopus.com/inward/record.url?scp=85063563755&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85063563755&partnerID=8YFLogxK
U2 - 10.22489/CinC.2018.093
DO - 10.22489/CinC.2018.093
M3 - Conference contribution
AN - SCOPUS:85063563755
T3 - Computing in Cardiology
BT - Computing in Cardiology Conference, CinC 2018
PB - IEEE Computer Society
T2 - 45th Computing in Cardiology Conference, CinC 2018
Y2 - 23 September 2018 through 26 September 2018
ER -