Premature Ventricular Contraction Beat Detection with Deep Neural Networks

A deep neural networks is proposed for the classification of premature ventricular contraction (PVC) beat, which is an irregular heartbeat initiated by Purkinje fibers rather than by sinoatrial node. Several machine learning approaches were proposed for the detection of PVC beats although they resulted in either achieving low accuracy of classification or using limited portion of data from existing electrocardiography (ECG) databases. In this paper, we propose an optimized deep neural networks for PVC beat classification. Our method is evaluated on TensorFlow, which is an open source machine learning platform initially developed by Google. Our method achieved overall 99.41% accuracy and a sensitivity of 96.08% with total 80,836 ECG beats including normal and PVC from the MIT-BIH Arrhythmia Database.

[1]  Shameer Faziludeen,et al.  ECG beat classification using wavelets and SVM , 2013, 2013 IEEE CONFERENCE ON INFORMATION AND COMMUNICATION TECHNOLOGIES.

[2]  Kyungtae Kang,et al.  Arrhythmia detection from heartbeat using k-nearest neighbor classifier , 2013, 2013 IEEE International Conference on Bioinformatics and Biomedicine.

[3]  Yoram Singer,et al.  Adaptive Subgradient Methods for Online Learning and Stochastic Optimization , 2011, J. Mach. Learn. Res..

[4]  G.G. Cano,et al.  An approach to cardiac arrhythmia analysis using hidden Markov models , 1990, IEEE Transactions on Biomedical Engineering.

[5]  Yu-Liang Hsu,et al.  ECG arrhythmia classification using a probabilistic neural network with a feature reduction method , 2013, Neurocomputing.

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

[7]  Farid Melgani,et al.  Classification of Electrocardiogram Signals With Support Vector Machines and Particle Swarm Optimization , 2008, IEEE Transactions on Information Technology in Biomedicine.

[8]  Willis J. Tompkins,et al.  A Real-Time QRS Detection Algorithm , 1985, IEEE Transactions on Biomedical Engineering.

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

[10]  Nuryani Nuryani,et al.  Premature ventricular contraction detection using swarm-based support vector machine and QRS wave features , 2014 .

[11]  G Bortolan,et al.  Premature ventricular contraction classification by the Kth nearest-neighbours rule , 2005, Physiological measurement.

[12]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

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

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

[15]  Reza Ebrahimpour,et al.  Classification of ECG arrhythmia by a modular neural network based on Mixture of Experts and Negatively Correlated Learning , 2013, Biomed. Signal Process. Control..

[16]  Kap Luk Chan,et al.  Classification of electrocardiogram using hidden Markov models , 1998, Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol.20 Biomedical Engineering Towards the Year 2000 and Beyond (Cat. No.98CH36286).

[17]  G. Moody,et al.  QRS morphology representation and noise estimation using the Karhunen-Loeve transform , 1989, [1989] Proceedings. Computers in Cardiology.

[18]  Mohammad Bagher Shamsollahi,et al.  Robust Detection of Premature Ventricular Contractions Using a Wave-Based Bayesian Framework , 2010, IEEE Transactions on Biomedical Engineering.