ABSTRACT
Several machine learning approaches have been proposed for classifying electrocardiogram (ECG) signals. Most of these use adaptive filtering techniques to reduce the noise corruption embedded in the signals. However, band-pass filters can affect the estimation of morphological parameters and result in misleading interpretation. We propose a noise-tolerant neural network (NN) approach, based on artificial noise injection, to improve the generalization capability of the resulting model. The NN classifier initially discriminated normal and abnormal heartbeat patterns in simulated ECG signals with minor, moderate, severe, and extreme noise, with an average accuracy of 99.2%, 95.1%, 91.4%, and 85.2% respectively. Ultimately we performed a fairly accurate recognition of four types of cardiac anomalies for single lead of raw ECG signals, obtained an overall classification accuracy of 95.7%. Therefore, is a useful tool for the detection and diagnosis of cardiac abnormalities.
- Hurxthal, L. M. 1934. Clinical interpretation of the electrocardiogram. N. Engl. J. Med. 211, 10, 431--437. Google ScholarCross Ref
- Wolff, A. R., Long, S., McComb, J. M., Richley, D., and Mercer, P. 2012. The gap between training and provision: a primary-care based ECG survey in North-East England. Br. J. Cardiol. 19, 1, 38--40. Google ScholarCross Ref
- Richley, D. 2013. New training and qualifications in electrocardiography. Br. J. Card. Nurs. 2013, 8, 1, 38--42. Google ScholarCross Ref
- Som, S. 2015. Nurse practitioners (and other physician extenders) are not an appropriate replacement for expert physician electrocardiogram readers in routine clinical practice. J. Am. Coll. Cardiol. 65, 1, 106--107. Google ScholarCross Ref
- Fitria, D., Ma'sum, M. A., Imah, E., and Gunawan, A. A. 2014. Automatic arrhythmias detection using various types of artificial neural network based learning vector quantization (LVQ). J. Comput. Sci. Inf. 7, 2, 93--103.Google Scholar
- Javadi, M., Arani, S. A. A. A, Sajedin, A., and Ebrahimpour, R. 2013. Classification of ECG arrhythmia by a modular neural network based on mixture of experts and negatively correlated learning. Biomed. Signal Process. Control. 8, 3, 289--296. Google ScholarCross Ref
- Rohan, M. D., and Patil, A. J. 2012. Layered approach for ECG beat classification utilizing neural network. Bioinformatics. 2, 6, 1495--1500.Google Scholar
- Wang, J. S., Chiang, W. C., Hsu, Y. L., and Yang, Y. T. C. 2013. ECG arrhythmia classification using a probabilistic neural network with a feature reduction method. Neurocomputing. 116, 38--45. Google ScholarCross Ref
- Karpagachelvi, S., Arthanari, M., and Sivakumar, M. 2012. Classification of electrocardiogram signals with support vector machines and extreme learning machine. Neural Comput. Appl. 21, 6, 1331--1339. Google ScholarDigital Library
- Khazaee, A., and Zadeh, A. E. 2014. ECG beat classification using particle swarm optimization and support vector machine. Front. Comput. Sci. 8, 2, 217--231. Google ScholarCross Ref
- Yeh, Y. C. 2012. An analysis of ECG for determining heartbeat case by using the principal component analysis and fuzzy logic. Int. J. Fuzzy Syst.14, 2, 233--241.Google Scholar
- Chua, T. W., and Tan, W. W. 2011. Non-singleton genetic fuzzy logic system for arrhythmias classification. Eng. Appl. Artif. Intell. 24, 2, 251--259. Google ScholarDigital Library
- Kher, R., Pawar, T., Thakar, V., and Shah, H. 2015. Physical activities recognition from ambulatory ECG signals using neuro-fuzzy classifiers and support vector machines. J. Med. Eng. Technol. 39, 2, 138--152. Google ScholarCross Ref
- Meau, Y. P., Ibrahim, F., Narainasamy, S. A., and Omar, R. 2006. Intelligent classification of electrocardiogram (ECG) signal using extended Kalman Filter (EKF) based neuro fuzzy system. Comput. Methods Programs Biomed. 82, 2, 157--168. Google ScholarDigital Library
- Zadeh, A. E., Khazaee, A., and Ranaee, V. 2010. Classification of the electrocardiogram signals using supervised classifiers and efficient features. Comput. Methods Programs Biomed. 99, 2, 179--194. Google ScholarDigital Library
- Micó, P., Mora, M., Cuesta-Frau, D., and Aboy, M. 2010. Automatic segmentation of long-term ECG signals corrupted with broadband noise based on sample entropy. Comput. Methods Programs Biomed. 98, 2, 118--129. Google ScholarDigital Library
- Choudhary, M., and Narwaria, R. P. 2012. Suppression of noise in ECG signal using low pass IIR filters. Int. J. Electron. Comput. Sci. Eng. 1, 4, 2238--2243.Google Scholar
- Li, Q., and Clifford, G. D. 2012. Signal quality and data fusion for false alarm reduction in the intensive care unit. J. Electrocardiol. 45, 6, 596--603. Google ScholarCross Ref
- Oweis, R., and Hijazi, L. 2006. A computer-aided ECG diagnostic tool. Comput. Methods Programs Biomed. 81, 3, 279--284. Google ScholarCross Ref
- Übeyli, E. D. 2009. Adaptive neuro-fuzzy inference system for classification of ECG signals using Lyapunov exponents. Comput. Methods Programs Biomed. 93, 3, 313--321. Google ScholarDigital Library
- Das, M. K., and Ari, S. 2013. ECG arrhythmia recognition using artificial neural network with S-transform based effective features. In Proceeding of Annual IEEE India Conference (Mumbai, India, December 13-15, 2013) INDICON '13. IEEE, 1--6. Google ScholarCross Ref
- Li, Q., Rajagopalan, C., and Clifford, G. D. 2014. A machine learning approach to multi-level ECG signal quality classification. Comput. Methods Programs Biomed. 117, 3, 435--447. Google ScholarDigital Library
- Redmond, S. J., Xie, Y., Chang, D., Basilakis, J., and Lovell N. H. 2012. Electrocardiogram signal quality measures for unsupervised telehealth environments. Physiol. Meas. 33, 9, 1517--1533. Google ScholarCross Ref
- Ambrose, M. 2008. ECG. Interpretación clínica. Manual Moderno. Buenos Aires.Google Scholar
- Chierici, F., Pignagnoli, L., and Embriaco, D. 2010. Modeling of the hydroacoustic signal and tsunami wave generated by seafloor motion including a porous seabed. J. Geophys. Res. 115, C3, 1--15. Google ScholarCross Ref
- Islam, M. K., Haque, A. N., Tangim, G., Ahammad, T., and Khondokar, M. R. H. 2012. Study and analysis of ECG signal using MATLAB & LABVIEW as effective tools. Int. J. Comput. Electr. Eng. 4, 3, 404--408. Google ScholarCross Ref
- Guda, M., Gasser, S., and El Mahallawy, M. S. 2014. MATLAB simulation comparison for different adaptive noise cancelation algorithms. In Proceedings of the International Conference on Digital Information, Networking, and Wireless Communications (Ostrava, Czech Republic, June 24-26, 2014). DINWC '14, Technical University of Ostrava, 68--73.Google Scholar
- Bille, K., Figueiras, D., Schamasch, P., Kappenberger, L., Brenner, J.,I., Meijboom, F. J., and Meijboom, E.J. 2006. Sudden cardiac death in athletes: the Lausanne Recommendations. Eur. J. Cardiovasc. Prev. Rehabil. 13, 6, 859--875. Google ScholarCross Ref
- Cools, E., and Missant, C. 2014. Junctional ectopic tachycardia after congenital heart surgery. Acta Anaesthesiol. Belg. 65, 1, 1--8.Google Scholar
- Das, M.K., Khan, B., Jacob, S., Kumar, A., and Mahenthiran, J. 2006. Significance of a fragmented QRS complex versus a Q wave in patients with coronary artery disease. Circulation. 113, 21, 2495--2501. Google ScholarCross Ref
- Valo, M., Moller, A., and Teupe, C. 2015. Markers of myocardial ischemia in patients with diabetes mellitus and severe obstructive sleep apnea impact of continuous positive airway pressure therapy. J. Diabetes Metab. 6, 492, 2--5.Google Scholar
- Bakhoya, V. N., Kurl, S., and Laukkanen, J. A. 2014. T-wave inversion on electrocardiogram is related to the risk of acute coronary syndrome in the general population. Eur. J. Prev. Cardiol. 21, 4, 500--506. Google ScholarCross Ref
- Bousseljot, R., Kreiseler, D., and Schnabel, A. 1995. Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomed. Tech. 40, s1, 317--318.Google Scholar
- Mainardi, L., Sornmo, L., and Cerutti, S. 2008. Understanding atrial fibrillation: the signal processing contribution. Morgan & Claypool Publishers, San Rafael.Google Scholar
- Ramli, A. B., and Ahmad, P. A. 2003. Correlation analysis for abnormal ECG signal features extraction. In Proceedings of 4th National Conference on Telecommunication Technology (Shah Alam, Malaysia, January 14-15, 2003). NCTT '03. IEEE, 232--237. Google ScholarCross Ref
- Szabó, B. T., van der Vaart, A. W., and van Zanten, J. H. 2013. mpirica a es sca in of aussian priors in the white noise model. Electron. J. Stat. 7, 991--1018. Google ScholarCross Ref
- Grandvalet, Y, and Canu, S. 1995. Comments on noise injection into inputs in back propagation learning. IEEE Trans. Syst. Man Cybern. 25, 4, 678--681. Google ScholarCross Ref
- An, G. 1996. The effects of adding noise during backpropagation training on a generalization performance. Neural Comput. 8, 3, 643--674. Google ScholarDigital Library
- Moody, G. B., and Mark, R. G. 2001. The impact of the MIT-BIH arrhythmia database. IEEE Eng. Med. Biol. Mag. 20, 3, 45--50. Google ScholarCross Ref
- Asl, B. M., Sharafat, A. R., and Setarehdan, S. K. 2012. An adaptive backpropagation neural network for arrhythmia classification using RR interval signal. Neural Netw. World. 6, 12, 535--54.Google ScholarCross Ref
- Garg, P., and Sharma, A. 2015. Detection of normal ECG and arrhythmia using artificial neural network system. Int. J. Eng. Res. Sci. Technol. 4, 1, 1--13.Google Scholar
- Moses, D. 2015. A survey of data mining algorithms used in cardiovascular disease diagnosis from multi-lead ECG data. Kuwait J. Sci. 42, 2, 206--235.Google Scholar
- Jadhav, S., Nalbalwar, S., and Ghatol, A. 2012. Performance evaluation of generalized feedforward neural network based ECG arrhythmia classifier. Int. J. Comput. Sci. Issues. 9, 4, 379--384.Google Scholar
- Kumar, R., Gupta, R., Jyoti, K., and Ranjan, A. K. 2015. AT89C51 microcontroller based medical two channel ECG module and body temperature measurement with graphics LCD. Int. J. Adv. Res. Comput. Sci. Softw. Eng. 5, 5, 1321--1326.Google Scholar
- Longini, R. L., Giolma, J. P., Wall III, C., and Quick, R. F. 1975. Filtering without phase shift. IEEE Trans. Biomed. Eng. BME-22, 5, 432--433. Google ScholarCross Ref
- Valverde, E. R., Quinteiro, R. A., Bertran, G. C., Arini, P. D., Glenny, P., and Biagetti, M.O. 1998. Influence of filtering techniques on the time domain analysis of signal-averaged P wave electrocardiogram. J. Cardiovasc. Electrophysiol. 9, 3, 253--260. Google ScholarCross Ref
- Lęski, J. M., Henzel, N. 2005. ECG baseline wander and powerline interference reduction using nonlinear filter bank. Signal Process. 85, 4, 781--793. Google ScholarDigital Library
- Gregg, R. E., Zhou S. H., Lindauer, J. M., Helfenbein, E. D., and Giuliano, K. K. 2008. What is inside the electrocardiograph?. J. Electrocardiol. 41, 1, 8--14. Google ScholarCross Ref
- Censi, F., Calcagnini, G., Triventi, M., Mattei, E., Bartolini, P., Corazza, I., and Boriani, G. 2009. Effect of high-pass filtering on ECG signal on the analysis of patients prone to atrial fibrillation. Ann. Ist. Super. Sanità. 45, 4, 427--431. Google ScholarCross Ref
- Berson, A.S., and Pipberger, H.V. 1966. The low-frequency response of electrocardiographs, a frequent source of recording errors. Am. Heart J. 71, 6, 779--789. Google ScholarCross Ref
- Bragg-Remschel, D. A., Anderson, C. M., and Winkle, R. A. 1982. Frequency response characteristics of ambulatory ECG monitoring systems and their implications for ST segment analysis. Am. Heart J. 1982, 103, 1, 20--31. Google ScholarCross Ref
- Tayler, D., and Vincent, R. 1983. Signal distortion in the electrocardiogram due to inadequate phase response. IEEE Trans Biomed Eng. BME-30, 6, 352--356. Google ScholarCross Ref
- Tayler, D. I, and Vincent, R. 1985. Artefactual ST segment abnormalities due to electrocardiograph design. Br. Heart J. 54, 2, 121--128. Google ScholarCross Ref
- Burri, H., Sunthorn, H., and Shah, D. 2006. Simulation of anteroseptal myocardial infarction by electrocardiographic filters. J. Electrocardiol. 39, 3, 253--258. Google ScholarCross Ref
- Buendía-Fuentes, F., Arnau-Vives, M. A., Arnau-Vives, A., Jiménez-Jiménez, Y., Rueda-Soriano, J., Zorio-Grima, E., Osa-Sáez, A., Martínez-Dolz, L. V., Almenar-Bonet, L., and Palencia-Pérez, M. A. 2012. High-bandpass filters in electrocardiography: source of error in the interpretation of the ST segment. Int. Sch. Res. Notices Cardiol. 2012, 1--10. Google ScholarCross Ref
- Li, B., Tsao, Y., and Sim, K. C. 2013. An investigation of spectral restoration algorithms for deep neural networks based noise robust speech recognition. In Proceedings of 14th Annual Conference of the International Speech Communication Association (Lyon, France, August 25-29, 2014). INTERSPEECH '13. Curran Associates, Inc, 3002--3006.Google Scholar
- Yin, S., Liu, C., Zhang, Z., Lin, Y., Wang, D., Tejedor, J., Fang-Zhen, T., and Li, Y. 2015. Noisy training for deep neural networks in speech recognition. EURASIP J. Audio Spee. 2015, 1, 1--14. Google ScholarCross Ref
Index Terms
- Noise-Tolerant Neural Network Approach for Electrocardiogram Signal Classification
Recommendations
A computationally efficient CNN-LSTM neural network for estimation of blood pressure from features of electrocardiogram and photoplethysmogram waveforms
AbstractContinuous blood pressure (BP) monitoring would significantly improve diagnosis and treatment of hypertension. Current at-home monitoring relies on uncomfortable and unreliable cuff-based devices, which are incapable of continuous ...
Using feed forward neural network for electrocardiogram signal analysis in chaotic domain
A feed forward neural network for classification of the Electrocardiogram (ECG) beats is employed in this paper. The classification is performed based on a feature extraction scheme. Six groups of ECG beats (MIT-BIH Normal Sinus rhythm, BIDMC congestive ...
The Classification of Hypertensive Retinopathy using Convolutional Neural Network
Changes in the retina of the eyes may occur due to high blood pressure, hypertensive retinopathy (HR) is a type of eye disease in which there is a change of the blood vessels of the eyes in the eye retina caused by arterial hypertension. HR signs occur ...
Comments