Efficient ECG classification based on Chi-square distance for arrhythmia detection

Abstract

This study introduces a new classifier tailored to address the limitations inherent in conventional classifiers such as K-nearest neighbor (KNN), random forest (RF), decision tree (DT), and support vector machine (SVM) for arrhythmia detection. The proposed classifier leverages the Chi-square distance as a primary metric, providing a specialized and original approach for precise arrhythmia detection. To optimize feature selection and refine the classifier's performance, particle swarm optimization (PSO) is integrated with the Chi-square distance as a fitness function. This synergistic integration enhances the classifier’s capabilities, resulting in a substantial improvement in accuracy for arrhythmia detection. Experimental results demonstrate the efficacy of the proposed method, achieving a noteworthy accuracy rate of 98% with PSO, higher than 89% achieved without any previous optimization. The classifier outperforms machine learning (ML) and deep learning (DL) techniques, underscoring its reliability and superiority in the realm of arrhythmia classification. The promising results render it an effective method to support both academic and medical communities, offering an advanced and precise solution for arrhythmia detection in electrocardiogram (ECG) data.

Keywords

Arrhythmia classification / Chi-square distance / Electrocardiogram (ECG) signal / Particle swarm optimization (PSO)

Data availability

The compiled MIT-BIH arrhythmia dataset is accessible through the provided link (https://github.com/dhiah-dev/Dataset-Compiled-ECG-MIT-BIH-Arrhythmia).

Declaration of competing interest

The authors declare no conflicts of interest.

References

[1] W.A. Zoghbi, T. Duncan, E. Antman, et al., Sustainable development goals and the future of cardiovascular health: a statement from the global cardiovascular disease taskforce, J. Am. Heart Assoc. 3 (5) (2014) e000504.

[2] U.R. Acharya, S.L. Oh, Y. Hagiwara, et al., A deep convolutional neural network model to classify heartbeats, Comput. Biol. Med. 89 (2017) 389-396.

[3] M.R. Homaeinezhad, S.A. Atyabi, E. Tavakkoli, H.N. Toosi, A. Ghaffari, R. Ebrahimpour, ECG arrhythmia recognition via a neuro-SVM-KNN hybrid classifier with virtual QRS image-based geometrical features, Expert Syst. Appl. 39 (2) (2012) 2047-2058.

[4] A. Mert, N. Kilic, A. Akan, ECG signal classification using ensemble decision tree, J. Trends Dev. Mach. Assoc. Technol. 16 (1) (2012) 179-182.

[5] F. Charfi, A. Kraiem, Comparative study of ECG classification performance using decision tree algorithms, Int. J. E-Health Med. C. 3 (4) (2012) 102-120.

[6] I. Saini, D. Singh, A. Khosla, QRS detection using K-nearest neighbor algorithm (KNN) and evaluation on standard ECG databases, J. Adv. Res. 4 (4) (2013) 331-344.

[7] I. Saini, D. Singh, A. Khosla, Delineation of ECG wave components using K-nearest neighbor (KNN) algorithm: ECG wave delineation using KNN, in: Proc. of 10th Intl. Conf. on Information Technology: New Generations, Las Vegas, USA, (2013), pp. 712-717.

[8] N. Kohli, N.K. Verma, Arrhythmia classification using SVM with selected features, Int. J. Eng. Sci. Technol. 3 (8) (2011) 122-131.

[9] S. Celin, K. Vasanth, ECG signal classification using various machine learning techniques, J. Med. Syst. 42 (12) (2018) 241:1-11.

[10] R.G. Kumar, Y.S. Kumaraswamy, Investigating cardiac arrhythmia in ECG using random forest classification, Int. J. Comput. Appl. 37 (4) (2012) 31-34.

[11] A.P. Razi, Z. Einalou, M. Manthouri, Sleep apnea classification using random forest via ECG, Sleep Vigil. 5 (1) (2021) 141-146.

[12] S.K. Pandey, R.R. Janghel, Automatic arrhythmia recognition from electrocardiogram signals using different feature methods with long short-term memory network model, Signal Image Video P. 14 (6) (2020) 1255-1263.

[13] B. Tutuko, S. Nurmaini, A.E. Tondas, et al., AFibNet: an implementation of atrial fibrillation detection with convolutional neural network, BMC Med. Inform. Decis. 21 (1) (2021) 26:1-17.

[14] E. Izci, M.A. Ozdemir, M. Degirmenci, A. Akan, Cardiac arrhythmia detection from 2D ECG images by using deep learning technique, in: Proc. of Medical Technologies Congress, Izmir, Turkey, (2019), pp. 1-4.

[15] S. Singh, S.K. Pandey, U. Pawar, R.R. Janghel, Classification of ECG arrhythmia using recurrent neural networks, Procedia Comput. Sci. 132 (2018) 1290-1297.

[16] J. Zhang, A.-P. Liu, M. Gao, X. Chen, X. Zhang, X. Chen, ECG-based multi-class arrhythmia detection using spatio-temporal attention-based convolutional recurrent neural network, Artif. Intell. Med. 106 (2020) 101856.

[17] M. Deshmane, S. Madhe, ECG based biometric human identification using convolutional neural network in smart health applications, in: Proc. of 4th Intl. Conf. on Computing Communication Control and Automation, Pune, India, (2018), pp. 1-6.

[18] A. Batra, V. Jawa, Classification of arrhythmia using conjunction of machine learning algorithms and ECG diagnostic criteria, Int. J. Biology and Biomedicine 1 (2016) 1-7.

[19] N. Singh, P. Singh, Cardiac arrhythmia classification using machine learning techniques, K. Ray, S.N. Sharan, S. Rawat, S.K. Jain, S. Srivastava, A. Bandyopadhyay (Eds.), Engineering Vibration, Communication and Information Processing, Springer, Singapore, (2019), pp. 469-480.

[20] A. Gupta, A. Banerjee, D. Babaria, K. Lotlikar, H. Raut, Prediction and classification of cardiac arrhythmia, S. Shakya, V.E. Balas, S. Kamolphiwong, K.-L. Du (Eds.), Sentimental Analysis and Deep Learning, Springer, Singapore, (2022), pp. 527-538.

[21] S. Sakib, M.M. Fouda, Z.M. Fadlullah, N. Nasser, W. Alasmary, A proof-of-concept of ultra-edge smart IoT sensor: a continuous and lightweight arrhythmia monitoring approach, IEEE Access 9 (2021) 26093-26106.

[22] S. Hiriyannaiah, G.M. Siddesh, M.H.M. Kiran, K.G. Srinivasa, A comparative study and analysis of LSTM deep neural networks for heartbeats classification, Health Technol.-Ger. 11 (3) (2021) 663-671.

[23] S. Shin, M.-G. Kang, G.-J. Zhang, J. Jung, Y.T. Kim, Lightweight ensemble network for detecting heart disease using ECG signals, Appl. Sci. 12 (7) (2022) 3291.

[24] M. Hammad, A.M. Iliyasu, A. Subasi, E.S.L. Ho, A.A. Abd, A multitier deep learning model for arrhythmia detection, IEEE T. Instrum. Meas. 70 (2020) 2502809.

[25] M. Hammad, S. Meshoul, P. Dziwiński, P. Pławiak, I.A. Elgendy, Efficient lightweight multimodel deep fusion based on ECG for arrhythmia classification, Sensors 22 (23) (2022) 9347.

[26] D. Wang, Y.-J. Si, W.-Y. Yang, G. Zhang, J. Li, A novel electrocardiogram biometric identification method based on temporal-frequency autoencoding, Electronics 8 (6) (2019) 667.

[27] M. Hammad, S.A. Chelloug, R. Alkanhel, et al., Automated detection of myocardial infarction and heart conduction disorders based on feature selection and a deep learning model, Sensors 22 (17) (2022) 6503.

[28] M.N. Dar, M.U. Akram, A. Usman, S.A. Khan, ECG biometric identification for general population using multiresolution analysis of DWT based features, in: Proc. of 2nd Intl. Conf. on Information Security and Cyber Forensics Cape Town, South Africa, (2015), pp. 5-10.

[29] D. Bratton, J. Kennedy, Defining a standard for particle swarm optimization, in: Proc. of IEEE Swarm Intelligence Symposium, (2007), pp. 120-127. Honolulu, USA.

[30] R. Bharti, A. Khamparia, M. Shabaz, G. Dhiman, S. Pande, P. Singh, Prediction of heart disease using a combination of machine learning and deep learning, Comput. Intel. Neurosc. 2021 (2021) 8387680.

[31] M. Kumari, P. Ahlawat, DCPM: an effective and robust approach for diabetes classification and prediction, Int. J. Inf. Technol. 13 (3) (2021) 1079-1088.

[32] P. Biswas, T. Samanta, Anomaly detection using ensemble random forest in wireless sensor network, Int. J. Inf. Technol. 13 (5) (2021) 2043-2052.

[33] D.K. Atal, M. Singh, Arrhythmia classification with ECG signals based on the optimization-enabled deep convolutional neural network, Comput. Meth. Prog. Bio. 196 (2020) 105607.

[34] J. Zhang, A.-P. Liu, D. Liang, X. Chen, M. Gao, Interpatient ECG heartbeat classification with an adversarial convolutional neural network, J. Healthc. Eng. 2021 (2021) 9946596.

[35] W.H. Jung, S.G. Lee, An arrhythmia classification method in utilizing the weighted KNN and the fitness rule, IRBM 38 (3) (2017) 138-148.

[36] M.-Z. Wu, Y.-D. Lu, W.-L. Yang, S.Y. Wong, A study on arrhythmia via ECG signal classification using the convolutional neural network, Front. Comput. Neurosc. 14 (2021) 564015.

[37] S.K. Pandey, R.R. Janghel, V. Vani, Patient specific machine learning models for ECG signal classification, Procedia Comput. Sci. 167 (2020) 2181-2190.

[38] M. Sharma, R.-S. Tan, U.R. Acharya, Automated heartbeat classification and detection of arrhythmia using optimal orthogonal wavelet filters, Inform. Med. Unlocked. 16 (2019) 100221.

[39] V. Mondéjar-Guerra, J. Novo, J. Rouco, M.G. Penedo, M. Ortega, Heartbeat classification fusing temporal and morphological information of ECGs via ensemble of classifiers, Biomed. Signal Proces. 47 (2019) 41-48.

[40] M.M. Farag, A tiny matched filter-based CNN for inter-patient ECG classification and arrhythmia detection at the edge, Sensors 23 (3) (2023). 1365.

[41] T. Wang, C.-H. Lu, W. Ju, C. Liu, Imbalanced heartbeat classification using EasyEnsemble technique and global heartbeat information, Biomed. Signal Proces. 71 (2022) 103105.

[42] Y.-R. Jin, J.-L. Liu, Y.-Q. Liu, et al., A novel interpretable method based on dual-level attentional deep neural network for actual multilabel arrhythmia detection, IEEE T. Instrum. Meas. 71 (2021) 2500311.

[43] M. Zubair, S. Woo, S. Lim, D. Kim, Deep representation learning with sample generation and augmented attention module for imbalanced ECG classification, IEEE J. Biomed. Health, (2023),10.1109/JBHI.2023.3325540.

[44] Y. Xia, Y.-Q. Xiong, K.-Q. Wang, A transformer model blended with CNN and denoising autoencoder for inter-patient ECG arrhythmia classification, Biomed. Signal Proces. 86 (Part C), (2023) 105271.