Abstract
Medical practitioners need to understand the critical features of ECG beats to diagnose and identify cardiovascular conditions accurately. This would be greatly facilitated by identifying the significant features of frequency components in temporal ECG wave-forms using computational methods. In this study, we have proposed a novel ECG beat classifier based on a customized VGG16-based Convolution Neural Network (CNN) that uses the time-frequency representation of temporal ECG, and a method to identify the contribution of interpretable ECG frequencies when classifying based on the SHapley Additive exPlanations (SHAP) values. We applied our model to the MIT-BIH arrhythmia dataset to classify the ECG beats and to characterise of the beats frequencies. This model was evaluated with two advanced time-frequency analysis methods. Our results indicated that for 2-4 classes our proposed model achieves a classification accuracy of 100% and for 5 classes it achieves a classification accuracy of 99.90%. We have also tested the proposed model using premature ventricular contraction beats from the American Heart Association (AHA) database and normal beats from Lobachevsky University Electrocardiography database (LUDB) and obtained a classification accuracy of 99.91% for the 5-classes case. In addition, SHAP value increased the interpretability of the ECG frequency features. Thus, this model could be applicable to the automation of the cardiovascular diagnosis system and could be used by clinicians.
Similar content being viewed by others
References
Benjamin EJ, Muntner P, Sommer MB. Heart disease and stroke statistics-2019 update: a report from the American heart association. Circulation. 2019;139(10):e56–528.
Narain SY, Kumar SSS, Kumar RA. Bioelectrical signals as emerging biometrics: issues and challenges; 2012. p. 2012.
Mohamed EAB, Dong GL, Makki AA, Gyeong MY, Eun-jong C, Jang-whan B, Myeong CC, Keun HR. Highlighting the current issues with pride suggestions for improving the performance of real time cardiac health monitoring. In: International Conference on Information Technology in Bio-and Medical Informatics, pp 226–233. Springer, 2010.
Shweta HJ, Vipul KD, Harshadkumar BP. Classification of ecg signals using machine learning techniques: a survey. In: 2015 International Conference on Advances in Computer Engineering and Applications, pp. 714–721. IEEE, 2015.
Rajendra AU, Paul JK, Kannathal N, Lim CM, Suri JS. Heart rate variability: a review. Med Biol Eng Comput. 2006;44(12):1031–51.
Marwa MAH, Mohamed IE, Ahmed F. Computer aided diagnosis of cardiac arrhythmias. In: 2006 International Conference on Computer Engineering and Systems, pp. 262–265. IEEE, 2006.
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.
Terrill F, David HW. A minicomputer system for direct high speed analysis of cardiac arrhythmia in 24 h ambulatory ecg tape recordings. IEEE Trans Biomed Eng. 1980;12:685–93.
Coast Douglas A, Stern Richard M, Cano Gerald G, Briller SA. An approach to cardiac arrhythmia analysis using hidden markov models. IEEE Trans Biomed Eng. 1990;37(9):826–36.
Lin K-P, Chang WH. Qrs feature extraction using linear prediction. IEEE Trans Biomed Eng. 1989;36(10):1050–5.
Farid M, Yakoub B. Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inf Technol Biomed. 2008;12(5):667–77.
Ge D, Srinivasan N, Krishnan SM. Cardiac arrhythmia classification using autoregressive modeling. Biomed Eng. 2002;1(1):5.
Mishra AK, Raghav S. Local fractal dimension based ecg arrhythmia classification. Biomed Signal Process Control. 2010;5(2):114–23.
Ali K, Ataollah E. Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features. Biomed Signal Process Control. 2010;5(4):252–63.
Linh TH, Osowski S, Stodolski M. On-line heart beat recognition using hermite polynomials and neuro-fuzzy network. IEEE Trans Instrum Meas. 2003;52(4):1224–311.
Martis RJ, Chakraborty C, Ray AK. A two-stage mechanism for registration and classification of ecg using gaussian mixture model. Pattern Recognit. 2009;42(11):2979–88.
Abdelhamid D, Latifa H, Naif A, Farid M. A wavelet optimization approach for ecg signal classification. Biomed Signal Process Control. 2012;7(4):342–9.
Martis RJ, Muthu RKM, Chakraborty C, Pal S, Sarkar D, Mandana KM, Ray AK. Automated screening of arrhythmia using wavelet based machine learning techniques. J Med Syst. 2012;36(2):677–88.
Hamid K, Majid M. A comparative study of dwt, cwt and dct transformations in ecg arrhythmias classification. Expert Syst Appl. 2010;37(8):5751–7.
Yu HH, 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.
Jiang W, Kong SG. Block-based neural networks for personalized ecg signal classification. IEEE Trans Neural Netw. 2007;18(6):1750–61.
Inan OT, Giovangrandi L, Kovacs GTA. Robust neural-network-based classification of premature ventricular contractions using wavelet transform and timing interval features. IEEE Trans Biomed Eng. 2006;53(12):2507–15.
Martis RJ, Rajendra AU, Mandana KM, Ray AK, Chakraborty C. Application of principal component analysis to ecg signals for automated diagnosis of cardiac health. Expert Syst Appl. 2012;39(14):11792–800.
Martis RJ, Rajendra AU, Mandana KM, Ray AK, Chakraborty C. Cardiac decision making using higher order spectra. Biomed Signal Process Control. 2013;8(2):193–203.
Rajendra AU, Fujita H, Shu LO, Raghavendra U, Tan JH, Adam M, Gertych Arkadiusz HY. Automated identification of shockable and non-shockable life-threatening ventricular arrhythmias using convolutional neural network. Fut Gen Comput Syst. 2018;79:952–9.
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.
Sannino G, De Pietro G. A deep learning approach for ecg-based heartbeat classification for arrhythmia detection. Fut Gen Comput Syst. 2018;86:446–55.
Mathews SM, Kambhamettu C, Barner KE. A novel application of deep learning for single-lead ecg classification. Comput Biol Med. 2018;99:53–62.
Rajendra AU, Hamido FO, Lih S, Hagiwara Y, Tan JH, Adam M. Automated detection of arrhythmias using different intervals of tachycardia ecg segments with convolutional neural network. Inf Sci. 2017;405:81–90.
Jambukia Shweta H, Dabhi Vipul K, Prajapati HB. Ecg beat classification using machine learning techniques. Int J Biomed Eng Technol. 2018;26(1):32–533.
Rajendra AU, Shu LO, Hagiwara Y, Tan JH, Adam M, Gertych A, Tan RS. A deep convolutional neural network model to classify heartbeats. Comput Biol Med. 2017;89:389–96.
Rajendra AU, Fujita H, Shu LO, Hagiwara Y, Tan JH, Adam M. Application of deep convolutional neural network for automated detection of myocardial infarction using ecg signals. Inf Sci. 2017;415:190–8.
Ali I, Selen O. Cardiac arrhythmia detection using deep learning. Procedia Comput Sci. 2017;120:268–75.
Rajendra AU, Fujita H, Shu LO, Hagiwara Y, Tan JH, Adam M, Tan RS. Deep convolutional neural network for the automated diagnosis of congestive heart failure using ecg signals. Appl Intell. 2019;49(1):16–27.
Karen S, Andrew Z. Very deep convolutional networks for large-scale image recognition. 2014. arXiv preprint arXiv:1409.1556
Moody George B, Mark RG. The impact of the mit-bih arrhythmia database. IEEE Eng Med Biol Mag. 2001;20(3):45–50.
R Mark, G Moody. Mit-bih database and software catalog, 1997.
Ziqian W, Xujian F, Cuiwei Y. A deep learning method to detect atrial fibrillation based on continuous wavelet transform. In: 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 1908–1912. IEEE, 2019.
Norden EH, Zheng S, Steven RL, Manli CW, Hsing HS, Quanan Z, Nai-Chyuan Y, Chi CT, Henry HL. The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond Ser A Math Phys Eng Sci. 1998;454(1971):903–95.
Scott M L, Su-In L. A unified approach to interpreting model predictions. In I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, R. Garnett, editors, Advances in Neural Information Processing Systems 30, pp. 4765–4774. Curran Associates, Inc., 2017.
Gabriel E, Joseph DJ, Pascal S, Scott L, Su-In L. Learning explainable models using attribution priors. 2019. arXiv preprint arXiv:1906.10670
Mukund S, Ankur T, Qiqi Y. Axiomatic attribution for deep networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 3319–3328. JMLR. org, 2017.
François C et al. Keras. https://github.com/fchollet/keras, 2015.
Ary LG, Luis ANA, Leon G, Jeffrey MH, Plamen CI, Roger GM, Joseph EM, George BM, Chung-Kang P, Stanley HE. Physiobank, physiotoolkit, and physionet: components of a new research resource for complex physiologic signals. Circulation. 2000;101(23):e215–20.
Kalyakulina A, Yusipov II, Moskalenko VA, Nikolskiy AV, Kozlov AA, Kosonogov KA, Zolotykh NY, Ivanchenko MV. Lobachevsky university electrocardiography database (version 1.0. 0). PhysioNet, 2020.
Rai HM, Chatterjee K. A novel adaptive feature extraction for detection of cardiac arrhythmias using hybrid technique mrdwt & mpnn classifier from ecg big data. Big Data Res. 2018;12:13–22.
Güler İnan, Übeylı Elif D. Ecg beat classifier designed by combined neural network model. Pattern Recognit. 2005;38(2):199–208.
Bahareh T, Adrian DCC, Shervin S. Classifying measured electrocardiogram signal quality using deep belief networks. In: 2017 IEEE International Instrumentation and Measurement Technology Conference (I2MTC), pp. 1–6. IEEE, 2017.
Serkan K, Turker I, Moncef G. Real-time patient-specific ecg classification by 1-d convolutional neural networks. IEEE Trans Biomed Eng. 2015;63(3):664–75.
Shu LO, Ng EYK, Tan RS, Rajendra AU. Automated diagnosis of arrhythmia using combination of cnn and lstm techniques with variable length heart beats. Comput Biol Med. 2018;102:278–87.
Gramatikov B, Brinker J, Yi-Chun S, Thakor NV. Wavelet analysis and time-frequency distributions of the body surface ecg before and after angioplasty. Comput Methods Progr Biomed. 2000;62(2):87–988.
Takano NK, Tsutsumi T, Suzuki H, Okamoto Y, Nakajima T. Time frequency power profile of qrs complex obtained with wavelet transform in spontaneously hypertensive rats. Comput Biol Med. 2012;42(2):205–12.
Takeshi T, Yoshiwo O, Nami K-T, Daisuke W, Hiroshi S, Kazunori S, Kuniaki I, Toshiaki N. Time-frequency analysis of the qrs complex in patients with ischemic cardiomyopathy and myocardial infarction. IJC Heart Ves. 2014;4:177–87.
Ernest W, Reynolds JR, Muller B, Anderson GJ, Muller BT. High-frequency components in the electrocardiogram: a comparative study of normals and patients with myocardial disease. Circulation. 1967;35(1):195–206.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Ethical approval
We have used publicly available data in our experiment. Therefore we do not need any ethical consent for this study.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rashed-Al-Mahfuz, M., Moni, M.A., Lio’, P. et al. Deep convolutional neural networks based ECG beats classification to diagnose cardiovascular conditions. Biomed. Eng. Lett. 11, 147–162 (2021). https://doi.org/10.1007/s13534-021-00185-w
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13534-021-00185-w