Predicting defibrillation success in out-of-hospital cardiac arrested patients: Moving beyond feature design

OBJECTIVE Optimizing timing of defibrillation by evaluating the likelihood of a successful outcome could significantly enhance resuscitation. Previous studies employed conventional machine learning approaches and hand-crafted features to address this issue, but none have achieved superior performance to be widely accepted. This study proposes a novel approach in which predictive features are automatically learned. METHODS A raw 4s VF episode immediately prior to first defibrillation shock was feed to a 3-stage CNN feature extractor. Each stage was composed of 4 components: convolution, rectified linear unit activation, dropout and max-pooling. At the end of feature extractor, the feature map was flattened and connected to a fully connected multi-layer perceptron for classification. For model evaluation, a 10 fold cross-validation was employed. To balance classes, SMOTE oversampling method has been applied to minority class. RESULTS The obtained results show that the proposed model is highly accurate in predicting defibrillation outcome (Acc = 93.6 %). Since recommendations on classifiers suggest at least 50 % specificity and 95 % sensitivity as safe and useful predictors for defibrillation decision, the reported sensitivity of 98.8 % and specificity of 88.2 %, with the analysis speed of 3 ms/input signal, indicate that the proposed model possesses a good prospective to be implemented in automated external defibrillators. CONCLUSIONS The learned features demonstrate superiority over hand-crafted ones when performed on the same dataset. This approach benefits from being fully automatic by fusing feature extraction, selection and classification into a single learning model. It provides a superior strategy that can be used as a tool to guide treatment of OHCA patients in bringing optimal decision of precedence treatment. Furthermore, for encouraging replicability, the dataset has been made publicly available to the research community.

[1]  Khashayar Khorasani,et al.  Deep Convolutional Neural Networks and Learning ECG Features for Screening Paroxysmal Atrial Fibrillation Patients , 2018, IEEE Transactions on Systems, Man, and Cybernetics: Systems.

[2]  Haibo He,et al.  Learning from Imbalanced Data , 2009, IEEE Transactions on Knowledge and Data Engineering.

[3]  Geoffrey E. Hinton,et al.  Deep Learning , 2015, Nature.

[4]  Hehua Zhang,et al.  Predict Defibrillation Outcome Using Stepping Increment of Poincare Plot for Out-of-Hospital Ventricular Fibrillation Cardiac Arrest , 2015, BioMed research international.

[5]  M. Copass,et al.  Influence of cardiopulmonary resuscitation prior to defibrillation in patients with out-of-hospital ventricular fibrillation , 1999, JAMA.

[6]  B. McNally,et al.  A composite model of survival from out-of-hospital cardiac arrest using the Cardiac Arrest Registry to Enhance Survival (CARES). , 2013, Resuscitation.

[7]  S. Morita,et al.  Amplitude spectral area: predicting the success of electric shock delivered by defibrillators with different waveforms. , 2013, The Tokai journal of experimental and clinical medicine.

[8]  H U Strohmenger,et al.  Analysis of the ventricular fibrillation ECG signal amplitude and frequency parameters as predictors of countershock success in humans. , 1997, Chest.

[9]  U. Raghavendra,et al.  Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network , 2018, Future Gener. Comput. Syst..

[10]  Irena Jekova,et al.  Defibrillation shock success estimation by a set of six parameters derived from the electrocardiogram , 2004, Physiological measurement.

[11]  H. Strohmenger,et al.  Predicting defibrillation success , 2008, Current opinion in critical care.

[12]  Saeed Babaeizadeh,et al.  Predicting defibrillation success in sudden cardiac arrest patients. , 2013, Journal of electrocardiology.

[13]  Kaifa Wang,et al.  Prediction of Defibrillation Outcome by Ventricular Fibrillation Waveform Analysis: A Clinical Review , 2013 .

[14]  Stig Steen,et al.  Treatment of out-of-hospital cardiac arrest with LUCAS, a new device for automatic mechanical compression and active decompression resuscitation. , 2005, Resuscitation.

[15]  Gust H. Bardy,et al.  Tripling Survival From Sudden Cardiac Arrest Via Early Defibrillation Without Traditional Education in Cardiopulmonary Resuscitation , 2002, Circulation.

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

[17]  William Robson Schwartz,et al.  ECG-based heartbeat classification for arrhythmia detection: A survey , 2016, Comput. Methods Programs Biomed..

[18]  Nopadol Uchaipichat,et al.  Improved prediction of defibrillation success for out-of-hospital VF cardiac arrest using wavelet transform methods. , 2004, Resuscitation.

[19]  V. Atanasoski,et al.  Unsupervised Classification of Premature Ventricular Contractions Based on RR Interval and Heartbeat Morphology , 2018, 2018 14th Symposium on Neural Networks and Applications (NEUREL).

[20]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

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

[22]  L. Hadzievski,et al.  ECG derived feature combination versus single feature in predicting defibrillation success in out-of-hospital cardiac arrested patients , 2018, Biomedical Physics & Engineering Express.

[23]  Mi He,et al.  Combining multiple ECG features does not improve prediction of defibrillation outcome compared to single features in a large population of out-of-hospital cardiac arrests , 2015, Critical Care.

[24]  Bertrand Massot,et al.  A support vector machine for predicting defibrillation outcomes from waveform metrics. , 2014, Resuscitation.

[25]  Roger D. White,et al.  High discharge survival rate after out-of-hospital ventricular fibrillation with rapid defibrillation by police and paramedics. , 1996, Annals of emergency medicine.

[26]  Arun Kumar Sangaiah,et al.  An intelligent learning approach for improving ECG signal classification and arrhythmia analysis , 2020, Artif. Intell. Medicine.

[27]  Ljupco Hadzievski,et al.  Deep Learning Approach for Highly Specific Atrial Fibrillation and Flutter Detection based on RR Intervals , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[28]  P. Steen,et al.  Independent evaluation of a defibrillation outcome predictor for out-of-hospital cardiac arrested patients. , 2005, Resuscitation.

[29]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[30]  R. Dzwonczyk,et al.  Signal analysis of the human electrocardiogram during ventricular fibrillation: frequency and amplitude parameters as predictors of successful countershock. , 1996, Annals of emergency medicine.

[31]  Geoffrey E. Hinton.  A Practical Guide to Training Restricted Boltzmann Machines , 2012, Neural Networks: Tricks of the Trade.

[32]  R O Cummins,et al.  Recommended guidelines for uniform reporting of data from out-of-hospital cardiac arrest: the Utstein Style. Task Force of the American Heart Association, the European Resuscitation Council, the Heart and Stroke Foundation of Canada, and the Australian Resuscitation Council. , 1991, Annals of emergency medicine.

[33]  Joe Bisera,et al.  Signal integral for optimizing the timing of defibrillation. , 2013, Resuscitation.

[34]  Trygve Eftestøl,et al.  Prediction of countershock success using single features from multiple ventricular fibrillation frequency bands and feature combinations using neural networks. , 2007, Resuscitation.

[35]  P. Steen,et al.  Delaying defibrillation to give basic cardiopulmonary resuscitation to patients with out-of-hospital ventricular fibrillation: a randomized trial. , 2003, JAMA.

[36]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[37]  Yongqin Li,et al.  Amplitude spectrum area to guide resuscitation-a retrospective analysis during out-of-hospital cardiopulmonary resuscitation in 609 patients with ventricular fibrillation cardiac arrest. , 2013, Resuscitation.

[38]  Jinsul Kim,et al.  An Automated ECG Beat Classification System Using Convolutional Neural Networks , 2016, 2016 6th International Conference on IT Convergence and Security (ICITCS).

[39]  U. Rajendra Acharya,et al.  Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network , 2017, Inf. Sci..

[40]  M. Brezocnik,et al.  Predicting defibrillation success by 'genetic' programming in patients with out-of-hospital cardiac arrest. , 2003, Resuscitation.

[41]  K. Monsieurs,et al.  A rule for early outcome classification of out-of-hospital cardiac arrest patients presenting with ventricular fibrillation. , 1998, Resuscitation.

[42]  D J Roe,et al.  Outcomes of rapid defibrillation by security officers after cardiac arrest in casinos. , 2000, The New England journal of medicine.

[43]  Kayvan Najarian,et al.  Non-linear dynamical signal characterization for prediction of defibrillation success through machine learning , 2012, BMC Medical Informatics and Decision Making.

[44]  Maaret Castrén,et al.  European Resuscitation Council Guidelines for Resuscitation 2010 Section 2. Adult basic life support and use of automated external defibrillators , 2010, Resuscitation.

[45]  Ronald Davis,et al.  Neural networks and deep learning , 2017 .

[46]  Geoffrey E. Hinton,et al.  Deep Boltzmann Machines , 2009, AISTATS.

[47]  Hidenori Kinoshita,et al.  Prompt prediction of successful defibrillation from 1-s ventricular fibrillation waveform in patients with out-of-hospital sudden cardiac arrest , 2011, Journal of Anesthesia.

[48]  U. Rajendra Acharya,et al.  A deep convolutional neural network model to classify heartbeats , 2017, Comput. Biol. Medicine.

[49]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[50]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[51]  Jin He,et al.  Real-Time Multilead Convolutional Neural Network for Myocardial Infarction Detection , 2018, IEEE Journal of Biomedical and Health Informatics.

[52]  Harlan M Krumholz,et al.  Trends in survival after in-hospital cardiac arrest. , 2012, The New England journal of medicine.

[53]  Wanchun Tang,et al.  Mechanisms of myocardial hypercarbic acidosis during cardiac arrest , 1995 .

[54]  J. N. Watson,et al.  Practical issues in the evaluation of methods for the prediction of shock outcome success in out-of-hospital cardiac arrest patients. , 2006, Resuscitation.

[55]  T. Eftestøl,et al.  Identifying approaches to improve the accuracy of shock outcome prediction for out-of-hospital cardiac arrest. , 2008, Resuscitation.

[56]  Andrew Y. Ng,et al.  Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks , 2017, ArXiv.

[57]  Unai Irusta,et al.  Application of Entropy-Based Features to Predict Defibrillation Outcome in Cardiac Arrest , 2016, Entropy.

[58]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[59]  J. Nolan,et al.  European Resuscitation Council guidelines for resuscitation 2005. Section 3. Electrical therapies: automated external defibrillators, defibrillation, cardioversion and pacing. , 2005, Resuscitation.

[60]  Naif Alajlan,et al.  Deep learning approach for active classification of electrocardiogram signals , 2016, Inf. Sci..

[61]  Xuan Zeng,et al.  HeartID: A Multiresolution Convolutional Neural Network for ECG-Based Biometric Human Identification in Smart Health Applications , 2017, IEEE Access.

[62]  Roger D. White,et al.  Part 6: electrical therapies: automated external defibrillators, defibrillation, cardioversion, and pacing: 2010 American Heart Association Guidelines for Cardiopulmonary Resuscitation and Emergency Cardiovascular Care. , 2010, Circulation.

[63]  Moncef Gabbouj,et al.  Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks , 2016, IEEE Transactions on Biomedical Engineering.