Atrial Fibrillation Detection by the Combination of Recurrence Complex Network and Convolution Neural Network

In this paper, R wave peak interval independent atrial fibrillation detection algorithm is proposed based on the analysis of the synchronization feature of the electrocardiogram signal by a deep neural network. Firstly, the synchronization feature of each heartbeat of the electrocardiogram signal is constructed by a Recurrence Complex Network. Then, a convolution neural network is used to detect atrial fibrillation by analyzing the eigenvalues of the Recurrence Complex Network. Finally, a voting algorithm is developed to improve the performance of the beat-wise atrial fibrillation detection. The MIT-BIH atrial fibrillation database is used to evaluate the performance of the proposed method. Experimental results show that the sensitivity, specificity, and accuracy of the algorithm can achieve 94.28%, 94.91%, and 94.59%, respectively. Remarkably, the proposed method was more effective than the traditional algorithms to the problem of individual variation in the atrial fibrillation detection.

[1]  Zhong-Ke Gao,et al.  Erratum: “Complex network from time series based on phase space reconstruction” [Chaos 19, 033137 (2009)] , 2010 .

[2]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[3]  Ki H. Chon,et al.  Time-Varying Coherence Function for Atrial Fibrillation Detection , 2013, IEEE Transactions on Biomedical Engineering.

[4]  Kristina M Ropella,et al.  Differentiation of atrial rhythms from the electrocardiogram with coherence spectra. , 2002, Journal of electrocardiology.

[5]  U. Rajendra Acharya,et al.  Automated detection of atrial fibrillation using Bayesian paradigm , 2013, Knowl. Based Syst..

[6]  H. Abarbanel,et al.  Determining embedding dimension for phase-space reconstruction using a geometrical construction. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[7]  Yuanyuan Wang,et al.  Atrial fibrillation detection using spectra of FSD recurrence complex network , 2014, 2014 International Conference on Audio, Language and Image Processing.

[8]  Behnaz Ghoraani,et al.  Rate-independent detection of atrial fibrillation by statistical modeling of atrial activity , 2015, Biomed. Signal Process. Control..

[9]  Jeffrey M. Hausdorff,et al.  Physionet: Components of a New Research Resource for Complex Physiologic Signals". Circu-lation Vol , 2000 .

[10]  Leif Sörnmo,et al.  Sequential characterization of atrial tachyarrhythmias based on ECG time-frequency analysis , 2004, IEEE Transactions on Biomedical Engineering.

[11]  C. Marchesi,et al.  Estimation of the power spectral density in nonstationary cardiovascular time series: assessing the role of the time-frequency representations (TFR) , 1996, IEEE Transactions on Biomedical Engineering.

[12]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[13]  Sheng Lu,et al.  Automatic Real Time Detection of Atrial Fibrillation , 2009, Annals of Biomedical Engineering.

[14]  Massimo Ruo Roch,et al.  Time–Frequency Analysis of the Endocavitarian Signal in Paroxysmal Atrial Fibrillation , 2012, IEEE Transactions on Biomedical Engineering.

[15]  Vaidotas Marozas,et al.  A Noise-Adaptive Method for Detection of Brief Episodes of Paroxysmal Atrial Fibrillation , 2013, Computing in Cardiology 2013.

[16]  Steffen Leonhardt,et al.  Automatic Detection of Atrial Fibrillation in Cardiac Vibration Signals , 2013, IEEE Journal of Biomedical and Health Informatics.

[17]  Paulo Carvalho,et al.  Detection of Atrial Fibrillation using model-based ECG analysis , 2008, 2008 19th International Conference on Pattern Recognition.

[18]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[19]  A. Bolz,et al.  Three different algorithms for identifying patients suffering from atrial fibrillation during atrial fibrillation free phases of the ECG , 2007, 2007 Computers in Cardiology.

[20]  Ki H. Chon,et al.  Atrial flutter and atrial tachycardia detection using Bayesian approach with high resolution time-frequency spectrum from ECG recordings , 2013, Biomed. Signal Process. Control..

[21]  E. Helfenbein,et al.  Improvements in atrial fibrillation detection for real-time monitoring. , 2009, Journal of electrocardiology.

[22]  L. Cao.  Practical method for determining the minimum embedding dimension of a scalar time series , 1997 .

[23]  M. AlGhatrif,et al.  A brief review: history to understand fundamentals of electrocardiography , 2012, Journal of community hospital internal medicine perspectives.

[24]  Behnaz Ghoraani,et al.  Developing an atrial activity-based algorithm for detection of atrial fibrillation , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[25]  Nikos Komodakis,et al.  Learning to compare image patches via convolutional neural networks , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Yann LeCun,et al.  Convolutional neural networks applied to house numbers digit classification , 2012, Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012).