Convolutional Recurrent Neural Networks to Characterize the Circulation Component in the Thoracic Impedance during Out-of-Hospital Cardiac Arrest

Pulse detection during out-of-hospital cardiac arrest remains challenging for both novel and expert rescuers because current methods are inaccurate and time-consuming. There is still a need to develop automatic methods for pulse detection, where the most challenging scenario is the discrimination between pulsed rhythms (PR, pulse) and pulseless electrical activity (PEA, no pulse). Thoracic impedance (TI) acquired through defibrillation pads has been proven useful for detecting pulse as it shows small fluctuations with every heart beat. In this study we analyse the use of deep learning techniques to detect pulse using only the TI signal. The proposed neural network, composed by convolutional and recurrent layers, outperformed state of the art methods, and achieved a balanced accuracy of 90% for segments as short as 3 s.

[1]  Trygve Eftestøl,et al.  Thoracic-impedance changes measured via defibrillator pads can monitor signs of circulation. , 2007, Resuscitation.

[2]  Martín Abadi,et al.  TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems , 2016, ArXiv.

[3]  Judy Powell,et al.  The impact of increased chest compression fraction on return of spontaneous circulation for out-of-hospital cardiac arrest patients not in ventricular fibrillation. , 2011, Resuscitation.

[4]  Harald Eikeland,et al.  The chain of survival. , 2006, Resuscitation.

[5]  Unai Irusta,et al.  Deep Learning for Pulse Detection in Out-of-Hospital Cardiac Arrest Using the ECG , 2018, 2018 Computing in Cardiology Conference (CinC).

[6]  Yoshua Bengio,et al.  Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling , 2014, ArXiv.

[7]  Colin Turner,et al.  Assessment of the impedance cardiogram recorded by an automated external defibrillator during clinical cardiac arrest* , 2010, Critical care medicine.

[8]  R. Berg,et al.  Global incidences of out-of-hospital cardiac arrest and survival rates: Systematic review of 67 prospective studies. , 2010, Resuscitation.

[9]  J. Soar,et al.  European Resuscitation Council Guidelines for Resuscitation 2015: Section 3. Adult advanced life support. , 2015, Resuscitation.

[10]  Unai Irusta,et al.  Circulation detection using the electrocardiogram and the thoracic impedance acquired by defibrillation pads. , 2016, Resuscitation.

[11]  Javier Del Ser,et al.  ECG-based pulse detection during cardiac arrest using random forest classifier , 2018, Medical & Biological Engineering & Computing.

[12]  Ronald M. Aarts,et al.  Photoplethysmography-Based Algorithm for Detection of Cardiogenic Output During Cardiopulmonary Resuscitation , 2015, IEEE Transactions on Biomedical Engineering.

[13]  Trygve Eftestøl,et al.  Automatic Identification of Return of Spontaneous Circulation During Cardiopulmonary Resuscitation , 2008, IEEE Transactions on Biomedical Engineering.

[14]  U. Irusta,et al.  A Reliable Method for Rhythm Analysis during Cardiopulmonary Resuscitation , 2014, BioMed research international.

[15]  L Schweiberer,et al.  Checking for breathing: evaluation of the diagnostic capability of emergency medical services personnel, physicians, medical students, and medical laypersons. , 1999, Annals of emergency medicine.

[16]  Yongqin Li,et al.  Detection of spontaneous pulse using the acceleration signals acquired from CPR feedback sensor in a porcine model of cardiac arrest , 2017, PloS one.

[17]  A. Nagdev,et al.  Point-of-care ultrasound use in patients with cardiac arrest is associated prolonged cardiopulmonary resuscitation pauses: A prospective cohort study. , 2018, Resuscitation.

[18]  Sofía Ruiz de Gauna,et al.  Circulation assessment by automated external defibrillators during cardiopulmonary resuscitation. , 2018, Resuscitation.

[19]  W. Dick,et al.  Checking the carotid pulse check: diagnostic accuracy of first responders in patients with and without a pulse. , 1996, Resuscitation.

[20]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[21]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..