Abstract
Arrhythmias such as Atrial Fibrillation (Afib), Atrial Flutter (Afl), and Ventricular Fibrillation (Vfib) are early indicators of Stroke and Sudden Cardiac Death, which are significant causes of death globally. Therefore, it is vital to detect patients with these conditions early. Manual inspection of ECG signals is tedious, time-consuming, and is limited by inter-observer variabilities. Further, it is challenging to accurately differentiate several types of arrhythmias in complex non-linear ECG signals. Computer-aided Decision Support Systems (CDSS) could be valuable in such a scenario. The CDSS uses machine learning techniques to learn the subtle differences in these rhythms and can be used for fast, accurate, repeated, and objective classification of arrhythmias. A novel CDSS has been proposed for the discrimination of normal rhythm (Nsr) from Afib, Afl, and Vfib using machine learning techniques. Predictive models have been developed for ECG segments of two durations: 2 s and 5 s. The number of samples from each of the four classes were balanced using synthetically generated samples with the ADASYN technique. Third-order cumulant images were determined from the ECG segments. 18 non-linear features, including entropies and other texture-based features, were extracted from the cumulant images, and significant features were selected using the t-test. The selected features were used to train several classifiers.On evaluating several different classifiers with the significant features using tenfold stratified cross-validation, the Random Forest classifier consistently performed better for both two and five second ECG duration studies. An accuracy of 98.2%, sensitivity of 98.1%, and specificity of 99.4% were obtained for the 2-s dataset. For the 5-s dataset, the accuracy, sensitivity, and specificity were 98.8%, 98.8%, and 99.6%, respectively. Due to the intermittent occurrence of arrhythmia, analysis of longer duration ECG signals will help detect the onset of critical episodes of arrhythmia more accurately. Since the proposed predictive models work effectively in detecting arrhythmia in two or five second ECG segments rather than single ECG beats, they have better clinical adaptability and can be incorporated into clinical monitoring systems.
Similar content being viewed by others
References
Acharya UR, Suri JS, Spaan JAE, Krishnan SM (2007) Advances in cardiac signal processing. Springer-Verlag, Berlin Heidelberg, New York
Acharya UR, Sree SV, Suri JS (2011) Automatic detection of epileptic EEG signals using higher order cumulant features. Int J Neural Syst 21:403–414. https://doi.org/10.1142/S0129065711002912 (PMID: 21956932)
Acharya UR, Fujita H, Adam M, Oh SL, Tan JH, Sudarshan VK, Koh JEW (2016) Automated characterization of arrhythmias using nonlinear features from tachycardia ECG beats. In: IEEE international conference on systems, man, and cybernetics, 2016.
Alfaouri M, Daqrouq K (2008) ECG signal denoising by wavelet transform thresholding. Am J Appl Sci 5:276–281. https://doi.org/10.3844/ajassp.2008.276.281
Ashtiyani M, Navaei Lavasani S, Asgharzadeh Alvar A, Deevband MR (2018) Heart rate variability classification using support vector machine and genetic algorithm. J Biomed Phys Eng. 8:423–434
Bonaccorso G (2018) Machine learning algorithms, 2nd Ed, Packt Publishing
Box JF (1987) Guinness, Gosset, Fisher, and small samples. Statist Sci. 2:45–52. http://www.jstor.org/stable/2245613.
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Desai U, Martis RJ, Acharya UR, Nayak CG, Seshikala G, Shetty KR (2016) Diagnosis of multiclass tachycardia beats using recurrence quantification analysis and ensemble classifiers. J Mech Med Biol. https://doi.org/10.1142/S0219519416400054
Du X, Dong J, Ma M (2071) Is atrial fibrillation a preventable disease? J Am Coll Cardiol 69:1968–1982. https://doi.org/10.1016/j.jacc.2017.02.020
Eibe F, Ian HW (1998) Generating accurate rule sets without global optimization. In: Fifteenth international conference on machine learning, pp 144–151
Fatma G (2020) Thresholding the maximum entropy. MATLAB Central File Exchange. https://www.mathworks.com/ matlabcentral/fileexchange /35158-thresholding-the-maximum-entropy. Accessed June 2020
Galloway MM (1975) Texture classification using gray level runs length. Comput Graph Image Process 4:172–179. https://doi.org/10.1016/S0146-664X(75)80008-6
Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):E215-20. https://doi.org/10.1161/01.cir.101.23.e215
Guiasu S, Shenitzer A (1985) The principle of maximum entropy. Mathematical Intelligencer 7:42. https://doi.org/10.1007/BF03023004
Han J, Kamber MM (2006) Data mining: concepts and techniques. Morgan Kaufmann 2nd edition.
He H, Bai Y, Garcia EA, Li S (2008) ADASYN: Adaptive synthetic sampling approach for imbalanced learning. In: IEEE international joint conference on neural networks (IEEE World Congress on Computational Intelligence), Hong Kong, 1322–1328. doi: https://doi.org/10.1109/IJCNN.2008.4633969
Hosmer D (2001) Applied Logistic Regression, 3rd Ed, Wiley.
Jing J, Huaifeng Z, Dechang P, Chenglong D (2018) A novel multi-module neural network system for imbalanced heartbeats classification. Expert Syst Appl 1:100003. https://doi.org/10.1016/j.eswax.2019.100003
Larose DT (2014) Discovering knowledge in data: an introduction to data mining, 2nd edn. Wiley Interscience, New Jersey
Manjunath BS, Ma WY (1996) Texture features for browsing and retrieval of image data. IEEE Trans Pattern Anal Mach Intell 18:837–842. https://doi.org/10.1109/34.531803
Martis RJ, Acharya UR, Prasad H, Chua KC, Lim CM, Suri JS (2013) Application of higher order statistics for atrial arrhythmia classification. Biomed Signal Process Control 8:888–900. https://doi.org/10.1016/j.bspc.2013.08.008
Martis RJ, Acharya UR, Adeli H, Prasad H, Tan JH, Chua KC, Too CL, Yeo SWJ, Tong L (2014) Computer-aided diagnosis of atrial arrhythmia using dimensionality reduction methods on transform domain representation. Biomed Signal Process Control 13:295–305. https://doi.org/10.1016/j.bspc.2014.04.001
Mathworks 2003. HOSA—higher order spectral analysis toolbox. https://www.mathworks.com/matlabcentral/fileexchange/3013-hosa-higher-order-spectral-analysis-toolbox
Mayer CC, Bachler M, Hörtenhuber M. et al. (2014) Selection of entropy-measure parameters for knowledge discovery in heart rate variability data. BMC Bioinformatics 15. https://doi.org/https://doi.org/10.1186/1471-2105-15-S6-S2
Moody G, Mark R (1983) A new method for detecting atrial fibrillation using R-R intervals. Comput Cardiol 10:227–230
Moody G, Mark RG (2001) The impact of the MIT-BIH arrhythmia database. IEEE Eng Med Biol 20:45–50. https://doi.org/10.1109/51.932724
Nikias CL (1993) Higher-order spectral analysis, engineering in medicine and biology society. In: Proceedings of the 15th annual international conference of the IEEE, 319
Nolle FM, Badura FK, Catlett JM, Bowser RW, Sketch MH (1986) CREI-GARD, a new concept in computerized arrhythmia monitoring systems. Comput Cardiol 13:515–518
Santos MS, Soares JP, Abreu PH, Araujo H, Santos J (2018) Cross-validation for imbalanced datasets: avoiding overoptimistic and overfitting approaches [Research Frontier]. IEEE Comput Intell Mag 13:59–76. https://doi.org/10.1109/MCI.2018.2866730
Singh BN, Tiwari A (2006) Optimal selection of wavelet basis function applied to ECG signal denoising. Digital Signal Process 16:275–287. https://doi.org/10.1016/j.dsp.2005.12.003
Singh AP, Singh B (2010) Texture features extraction in mammograms using non-shannon entropies. Lecture notes in electrical engineering. Springer, Netherlands, pp 341–351
Shaker AM, Tantawi M, Shedeed HA, Tolba MF (2020) Generalization of Convolutional Neural Networks for ECG Classification Using Generative Adversarial Networks. IEEE Access 8:35592–35605. https://doi.org/10.1109/ACCESS.2020.2974712
Wang Y, Zhu YS, Thakor NV, Xu YH (2001) A short-time multifractal approach for arrhythmia detection based on fuzzy neural network. IEEE Trans Biomed Eng 48:989–995. https://doi.org/10.1109/10.942588
Author information
Authors and Affiliations
Corresponding author
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
Pham, TH., Sree, V., Mapes, J. et al. A novel machine learning framework for automated detection of arrhythmias in ECG segments. J Ambient Intell Human Comput 12, 10145–10162 (2021). https://doi.org/10.1007/s12652-020-02779-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12652-020-02779-1