Abstract
Deep learning applied to electrocardiogram (ECG) data can be used to achieve personal authentication in biometric security applications, but it has not been widely used to diagnose cardiovascular disorders. We developed a deep learning model for the detection of arrhythmia in which time-sliced ECG data representing the distance between successive R-peaks are used as the input for a convolutional neural network (CNN). The main objective is developing the compact deep learning-based detect system which minimally uses the dataset but delivers the confident accuracy rate of the arrhythmia detection. This compact system can be implemented in wearable devices or real-time monitoring equipment because the feature extraction step is not required for complex ECG waveforms, only the R-peak data is needed. The 10 hidden layers of the CNN detect arrhythmias using a novel RR-interval framing (RRIF) approach. Two testing processes were implemented, the first during the training and validation of the CNN algorithm and the second using different datasets for testing under realistic conditions. The results of both tests indicated that the Compact Arrhythmia Detection System (CADS) matched the performance of conventional systems for the detection of arrhythmia in two consecutive test runs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kim S-K, Yeun CY et al (2019) A machine learning framework for biometric authentication using electrocardiogram. IEEE Access 7:94858–94868
Alzaabi E, Kim S-K et al (2019) Electrocardiogram biometric authentication system by using machine learnings. IEEE Access 7:123069–123075
Kim S-K, Yeun CY et al (2019) An enhanced machine learning-based biometric authentication system using RR-interval framed electrocardiograms. IEEE Access 7:168669–168674
Luz EJ, Schwartz WR et al. (2016) ECG-based heartbeat classification for arrhythmia detection: a survey. Comput Methods Programs Biomed 127:144–164
Islam MR, Hossain R (2015) Arrhythmia detection technique using basic ECG parameters. Int J Comput Appl 119:11–15
Pummer C (2016) Continuous biometric authentication using electrocardiographic (ECG) data. https://usmile.at/publications. Accessed 1 Apr 2019
Zhang Q, Zhou D, Zeng X (2017) HeartID: a multi resolution convolution neural network for ECG-based biometrics human identification in smart health applications. IEEE Access 5:11805–11816
Pinto JR, Cardoso JS, Lourenco A (2018) Evolution, current challenges, and future possibilities in ECG biometrics. IEEE Access 6:34746–34776
Luz EIS, Moreira GJP, Oliveira LS et al. (2018) Learning deep off-the-person heart biometrics representations. IEEE Trans Inf Forensics Secur 13:1258–1270
Kim H, Chun SY (2019) Cancelable ECG biometrics using compressive sensing-generalized likelihood ratio test. IEEE Access 7:9232–9242
Guennoun M, Abbad N et al. (2009) Continuous authentication by electrocardiogram data. In: IEEE Toronto international conference science and technology for humanity, Toronto, ON, pp 40–42
Spach MS, Kootsey JM (1983) The nature of electrical propagation in cardiac muscle. Am J Physiol Heart Circ Physiol 244:3–22
McGraw R, Lord J et al. (2019) analysis and interpretation of the electrocardiogram, https://meds.queensu.ca/central/assets/modules/ts-ecg/index.html. Accessed 1 Apr 2019
Goldberger AL, Amaral LAN et al (2000) Physiobank, physio toolkit, and physioNnt: components of a new research resource for complex physiologic signals. Circulation 101:e215–e220
Gacek A, Pedrycz W (2012) ECG signal processing, classification and interpretation. Springer, New York, NY
Kachuee M, Fazeli S et al. (2018) ECG heartbeat classification: a deep transferable representation. In: 2018 IEEE international conference on healthcare informatics, New York, NY, 443–444
Bhatti AT, Kim JH (2015) R-peak detection in ECG signal compression for heartbeat rate patients at 1KHz using high order statistic algorithm. J Multidisciplin Eng Sci Tech 2:2509–2515
Zhong W, Liao L et al. (2019) A deep learning approach for fetal QRS complex detection. Physiologic Measur 39(4):045004
Bennett FH et al. (1996) Automated design of both the topology and sizing of analog electrical circuits using genetic programming. In: Artificial Intelligence in Design, vol 96. Springer, Dordrecht, pp 151–170
Minchole A, Rodriguez B (2019) Artificial intelligence for the electrocardiogram. Nat Med 25:22–23
Tatara E, Cinar A (2002) Interpreting ECG data by integrating statistical and artificial intelligence tools. IEEE Eng Med Biol Mag 21:36–41
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Advances. In: Neural information processing systems, pp 1097–1105
Yu H, Xie T et al. (2011) Comparison of different neural network architectures for digit image recognition. In: Proceeding IC-HIS. Yokohama, Japan, pp 98–103
Weiss SM, Kapouleas I (1989) An empirical comparison of pattern recognition, neural nets, and machine learning classification methods. In: Proceedings IJCAI. https://www.ijcai.org/Proceedings/89-1/Papers/125.pdf. Accessed 1 Apr 2019
Szandal T (2015) Comparison of different learning algorithms for pattern recognition with hopfield’s neural network. Proc Comput Sci 71:68–75
Roopa CK, Harish BS (2017) A survey on various machine learning approaches for ECG analysis. Int J Comput Appl 163:25–33
Kiranyaz S, Ince T et al (2016) Real-time patient-specific ECG classification by 1-D convolutional neural networks. IEEE Tran Biomed Eng 63:664–675
Rajpurkar R, Hannun AY et al (2019) Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med 25:65–69
Mitra M, Samanta RK (2013) Cardiac arrhythmia classification using neural networks with selected features. Procedia Technol 10:76–84
Mondejar-Guerraa V, Novo J et al (2019) Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers. Biomed Signal Process Contr 47:41–48
Isina A, Ozdalilib S (2017) Cardiac arrhythmia detection using deep learning. Proc Comput Sci 120:268–275
Gerven M, Bohte S(2017) Artificial neural networks as models of neural information processing. Front Comput Neurosci. https://www.frontiersin.org/articles/https://doi.org/10.3389/fncom.2017.00114/full. Accessed 1 April 2019
Yann L (2019) LeNet-5, Convolutional neural networks. http://yann.lecun.com/exdb/lenet/. Accessed 1 Apr 2019
Yu W, Yang K et al. (2012) Visualizing and comparing convolutional neural networks. https://arxiv.org/abs/1412.6631. Accessed 1 Apr 2019
Taddei A, Distante G et al (1992) The European ST-T database: standard for evaluating systems for the analysis of ST-T changes in ambulatory electrocardiography. Eur Heart J 13:1164–1172
ANSI/AAMI (2008) Testing and reporting performance results of cardiac rhythm and ST segment measurement algorithms, American National Standards Institute, Inc. (ANSI), Association for the Advancement of Medical Instrumentation (AAMI), ANSI/AAMI/ISO EC57. 1998–(R)2008
Pater C (2005) Methodological considerations in the design of trials for safety assessment of new drugs and chemical entities. Trials 6(1):1–13
Cadogan M (2019) PR Interval. https://litfl.com/pr-interval-ecg-library/. Accessed 1 Apr 2019
Afonso VX, Tompkins WJ et al (1999) ECG beat detection using filter banks. IEEE Trans Biomed Eng 46:192–202
Hu YH, Tompkins WJ, Urrusti JL, Afonso VX (1993) App of artificial neural networks for ECG signal detection and classification, J Eletrocardiol 26:66–73
Xiang X, Lin Z, Meng J (2018) Automatic QRS complex detection using two-level convolutional neural network. BioMed Eng OnLine 17:13. https://biomedical-engineering-online.biomedcentral.com/articles/https://doi.org/10.1186/s12938-018-0441-4. Accessed 1 Jan 2020
Alarsan FI, Younes M (2019) Analysis and classification of heart diseases using heartbeat features and machine learning algorithms. J Big Data 6(8):1–15
Imam MH, Karmakar CK et al (2016) Detecting subclinical diabetic cardiac autonomic neuropathy by analyzing ventricular repolarization dynamics. IEEE J Biomed Health Inf 20:64–72
Moody GB, Mark RG (2001) The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol 20:45–50
Straeter TA On the extension of the Davidon-Broyden class of rank one, Quasi-newton minimization methods to an infinite dimensional Hilbert space with applications to optimal control problems. NASA Technical Reports Server. NASA
Viana M (2019) Loss Functions. https://ml-cheatsheet.readthedocs.io/en/latest/loss_functions.html. Accessed 1 Apr 2019
Aspuru J, Ochoa-Brust A et al. (2019) Segmentation of the ECG signal by means of a linear regression algorithm. Sensors 19(4):775. https://doi.org/10.3390/s19040775
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Kim, SK., Yeun, C.Y., Yoo, P.D., Lo, NW., Damiani, E. (2023). Deep Learning-Based Arrhythmia Detection Using RR-Interval Framed Electrocardiograms. In: Yang, XS., Sherratt, R.S., Dey, N., Joshi, A. (eds) Proceedings of Eighth International Congress on Information and Communication Technology. ICICT 2023. Lecture Notes in Networks and Systems, vol 694. Springer, Singapore. https://doi.org/10.1007/978-981-99-3091-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-3091-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-3090-6
Online ISBN: 978-981-99-3091-3
eBook Packages: EngineeringEngineering (R0)