Inter-patient ECG classification with convolutional and recurrent neural networks

• Autorzy: Guo Li , Sim Gavin , Matuszewski Bogdan

Identyfikatory

DOI

10.1016/j.bbe.2019.06.001

• Języki publikacji: EN

Abstrakty

EN

The recent advances in ECG sensor devices provide opportunities for user self-managed auto-diagnosis and monitoring services over the internet. This imposes the requirements for generic ECG classification methods that are inter-patient and device independent. In this paper, we present our work on using the densely connected convolutional neural network (DenseNet) and gated recurrent unit network (GRU) for addressing the inter-patient ECG classification problem. A deep learning model architecture is proposed and is evaluated using the MIT-BIH Arrhythmia and Supraventricular Databases. The results obtained show that without applying any complicated data pre-processing or feature engineering methods, both of our models have considerably outperformed the state-of-the-art performance for supraventricular (SVEB) and ventricular (VEB) arrhythmia classifications on the unseen testing dataset (with the F1 score improved from 51.08 to 61.25 for SVEB detection and from 88.59 to 89.75 for VEB detection respectively). As no patient-specific or device-specific information is used at the training stage in this work, it can be considered as a more generic approach for dealing with scenarios in which varieties of ECG signals are collected from different patients using different types of sensor devices.

Słowa kluczowe

EN

ECG classification; convolutional neural network; recurrent neural network; big data; deep learning

PL

klasyfikacja sygnału EKG; konwolucyjna sieć neuronowa; rekurencyjna sieć neuronowa; uczenie głębokie

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2019
• Tom: Vol. 39, no. 3
• Strony: 868--879
• Opis fizyczny: Bibliogr. 49 poz., rys., tab., wykr.

Twórcy

autor

Guo Li

• School of Physical Sciences & Computing, The University of Central Lancashire, Preston, United Kingdom

autor

Sim Gavin

• School of Physical Sciences & Computing, The University of Central Lancashire, Preston, United Kingdom

autor

Matuszewski Bogdan

• School of Engineering, The University of Central Lancashire, Preston, United Kingdom

Bibliografia

• [1] Kim H, Kim S, Van Helleputte N, Artes A, Konijnenburg M, Huisken J, et al. A configurable and low-power mixed signal SoC for portable ECG monitoring applications. IEEE Trans Biomed Circuits Syst 2014;8(2):257–67.
• [2] Mehta DD, Nazir NT, Trohman RG, Volgman AS. Single-lead portable ECG devices: perceptions and clinical accuracy compared to conventional cardiac monitoring. J Electrocardiol 2015;48(4):710–6.
• [3] Li Y, Guo L, Guo Y. Enabling health monitoring as a service in the cloud. IEEE/ACM 7th International Conference on Utility and Cloud Computing. 2014. pp. 127–36.
• [4] Mathews SM, Kambhamettu C, Barner KE. A novel application of deep learning for single-lead ECG classification. Comput Biol Med 2018;99:53–62.
• [5] De Chazal P, O'Dwyer M, Reilly RB. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng 2004;51(7):1196–206.
• [6] Hu YH, Palreddy S, Tompkins WJ. A patient-adaptable ECG beat classifier using a mixture of experts approach. IEEE Trans Biomed Eng 1997;44(9):891–900.
• [7] Al Rahhal MM, Bazi Y, AlHichri H, Alajlan N, Melgani F, Yager RR. Deep learning approach for active classification of electrocardiogram signals. Inf Sci 2016;345:340–54.
• [8] Chauhan S, Vig L. Anomaly detection in ECG time signals via deep long short-term memory networks. IEEE International Conference on Data Science and Advanced Analytics (DSAA). 2015. pp. 1–7.
• [9] Tracey BH, Miller EL. Nonlocal means denoising of ECG signals. IEEE Trans Biomed Eng 2012;59(9):2383–6.
• [10] Sameni R, Shamsollahi MB, Jutten C, Clifford GD. A nonlinear Bayesian filtering framework for ECG denoising. IEEE Trans Biomed Eng 2007;54(12):2172–85.
• [11] Hoekema R, Uijen GJH, Van Oosterom A. Geometrical aspects of the interindividual variability of multilead ECG recordings. IEEE Trans Biomed Eng 2001;48(5):551–9.
• [12] Wiens J, Guttag JV. Active learning applied to patient-adaptive heartbeat classification. Advances in Neural Information Processing Systems. 2010. pp. 2442–50.
• [13] Kiranyaz S, Ince T, Gabbouj M. Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Trans Biomed Eng 2016;63(3):664–75.
• [14] Kiranyaz S, Ince T, Gabbouj M. Personalized monitoring and advance warning system for cardiac arrhythmias. Sci Rep 2017;7(1):9270.
• [15] Huang G, Liu Z, van der Maaten L, Weinberger KQ. Densely connected convolutional networks; 2016.
• [16] Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling; 2014.
• [17] Gregor K, Danihelka I, Graves A, Rezende DJ, Wierstra D. DRAW: a recurrent neural network for image generation; 2015.
• [18] De Chazal P, O'Dwyer M, Reilly RBRB, deChazal P, O'Dwyer M, Reilly RBRB. Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng 2004;51(7):1196–206.
• [19] de Chazal P, Reilly RB. A patient-adapting heartbeat classifier using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng 2006;53(12):2535–43.
• [20] de Chazal P. Detection of supraventricular and ventricular ectopic beats using a single lead ECG. 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). 2013. pp. 45–8.
• [21] Llamedo M, Martínez JP. Heartbeat classification using feature selection driven by database generalization criteria. IEEE Trans Biomed Eng 2011;58(3):616–25.
• [22] Ince T, Kiranyaz S, Gabbouj M. A generic and robust system for automated patient-specific classification of ECG signals. IEEE Trans Biomed Eng 2009;56(5):1415–26.
• [23] Herlocker JL, Konstan JA. Content-independent task-focused recommendation. IEEE Internet Comput 2001;5 (6):40–7.
• [24] Jiang X, Zhang L, Zhao Q, Albayrak S. ECG arrhythmias recognition system based on independent component analysis feature extraction. TENCON 2006 – 2006 IEEE Region 10 Conference. 2006. pp. 1–4.
• [25] Senhadji L, Carrault G, Bellanger JJ, Passariello G. Comparing wavelet transforms for recognizing cardiac patterns. IEEE Eng Med Biol Mag 1995;14(2):167–73.
• [26] de Lannoy G, Francois D, Delbeke J, Verleysen M. Weighted conditional random fields for supervised interpatient heartbeat classification. IEEE Trans Biomed Eng 2012;59 (1):241–7.
• [27] Rodriguez J, Goni A, Illarramendi A. Real-time classification of ECGs on a PDA. IEEE Trans Inf Technol Biomed 2005;9 (1):23–34.
• [28] Jiang W, Kong SG. Block-based neural networks for personalized ECG signal classification. IEEE Trans Neural Netw 2007;18(6):1750–61.
• [29] Lagerholm M, Peterson C, Braccini G, Edenbrandt L, Sornmo L. Clustering ECG complexes using Hermite functions and self-organizing maps. IEEE Trans Biomed Eng 2000;47 (7):838–48.
• [30] Bengio Y, Courville A, Vincent P. Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Mach Intell 2013;35(8):1798–828.
• [31] Hinton GE, Osindero S, Teh Y-W. A fast learning algorithm for deep belief nets. Neural Comput 2006;18(7):1527–54.
• [32] Vincent P, Larochelle H, Bengio Y, Manzagol P-A. Extracting and composing robust features with denoising autoencoders. Proceedings of the 25th International Conference on Machine Learning; 2008. p. 1096–103.
• [33] LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series. Handb Brain Theory Neural Netw 1995;3361(10):1995.
• [34] Donida Labati R, Muñoz E, Piuri V, Sassi R, Scotti F. Deep- ECG: convolutional neural networks for ECG biometric recognition. Pattern Recognit Lett 2018.
• [35] Yan Y, Qin X, Wu Y, Zhang N, Fan J, Wang L. A restricted Boltzmann machine based two-lead electrocardiography classification. IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN). 2015. pp. 1–9.
• [36] Wang D, Shang Y. Modeling physiological data with deep belief networks. Int J Inf Educ Technol 2013;3(5):505–11.
• [37] Zubair M, Kim J, Yoon C. An automated ECG beat classification system using convolutional neural networks. 6th International Conference on IT Convergence and Security (ICITCS). 2016. pp. 1–5.
• [38] Acharya UR, Fujita H, Oh SL, Raghavendra U, Tan JH, Adam M, et al. Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network. Future Gener Comput Syst 2018;79:952–9.
• [39] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition; 2015.
• [40] Rajpurkar P, Hannun A, Haghpanahi M, Bourn C, Ng AY. Cardiologist-level arrhythmia detection with convolutional neural networks. arXiv preprint arXiv:1707.01836; 2017.
• [41] Albert D, Satchwell BR, Barnett KN. Wireless, ultrasonic personal health monitoring system. Google Patents; 2012.
• [42] Mikolov T, Karafiát M, Burget L, Cernocký J, Khudanpur S. Recurrent neural network based language model. Interspeech, vol. 2. 2010;p. 3.
• [43] Salloum R, Kuo C-CJ. ECG-based biometrics using recurrent neural networks. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). 2017. pp. 2062–6.
• [44] Zihlmann M, Perekrestenko D, Tschannen M. Convolutional recurrent neural networks for electrocardiogram classification; 2017.
• [45] Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift; 2015.
• [46] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521(7553):436–44.
• [47] Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 2000;101(23):E215–20.
• [48] ECAR A. Recommended practice for testing and reporting performance results of ventricular arrhythmia detection algorithms. Association for the Advancement of Medical Instrumentation; 1987.
• [49] Kingma DP, Ba J. Adam: a method for stochastic optimization; 2014.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2019).