Detection of healthy and unhealthy cardiac signals based on deep learning using convolutional neural network

Subject Areas :

Alireza nasrabadian ¹ , mohammad amin nooshzadeh ² , madiha abbas zadeh barani ³ , mohammad mahdi moradi ^{4 *}

1 - Department of Electrical Engineering, Kerman Branch, Shahid Chamran University, Kerman, Iran
2 - Department of Electrical Engineering, Kerman Branch, Shahid bahonar University, Kerman, Iran
3 - Department of Electrical Engineering, Kerman Branch, Islamic Azad University, Tehran, Iran
4 - Department of Electrical Engineering, Kerman Branch, Shahid Chamran University, Kerman, Iran

Received: 2023-10-11 Accepted : 2023-11-25 Published : 2023-12-10

Keywords: Electrocardiogram signal, deep learning, healthy and unhealthy heart signal.,

Abstract :

According to the statements of the World Organization, the most important factor threatening humans is cardiac arrhythmias. According to the latest global health statistics, nearly 50% of deaths are due to heart diseases. According to research, 25% of deaths due to heart diseases can be revived with timely and correct diagnosis. The electrocardiogram signal is the most important and dependent signal related to the heart. Registration of this signal is low-cost, fruitful, and powerful in detecting arrhythmias. Feature extraction is the most important part of recognition and processing. Deep features based on convolutional neural networks are very powerful and can be done without manual intervention. In this article, deep features are extracted using deep learning based on a convolutional neural network. Then the classification results were calculated with an average accuracy of 99.3% and an average sensitivity of 99.1% with 10-fold cross-validation. According to the obtained results, it can be said that the proposed method has the ability to classify cardiac arrhythmias with acceptable accuracy.

References:

[1] Eduardo Jose da S. Luza, William Robson Schwartzb, Guillermo Cámara-Cháveza, David MenottiacECG- based heartbeat classification for arrhythmia detection: a survey,journal of Computer Methods and Programs in Biomedicine, 127 (April 2016), pp. 144-164.
[2]G. Sannino, G. De Pietro, A deep learning approach for ECG-based heartbeat classification for arrhythmia detection, journal of Future Generation Computer Systems ELSEVIER (2018), pp. 446-455.
[3]Shalin Savalia, Vahid Emamian, Cardiac arrhythmia classification by multi-layer perceptron and convolution neural networks, MPDIbioeng., 5 (2018).
[4]G. Smaoui, A. Young, M. Abid, Single scale CWT algorithm for ECG beat detection for a portable monitoring system, J. Med. Biol.Eng, 37 (1) (2017), pp. 132-139.
[5]S.H. Jambukia, V.K. Dabhi, H.B. Prajapati, Classification of ECG signals using machine learning techniques: a survey, International Conference on Advances in Computer Engineering and Applications, IEEE (2015), pp. 714-721.
[6]M. Alfaras, M.C. Soriano, S. Ortín, A fast machine learning model for ECG-based heartbeat classification and arrhythmia detection, Front. Physiol., 7 (2019), p. 103
[7]M. Padmanabhan, P. Yuan, G. Chada, H.V. Nguyen, Physician-friendly machine learning: a case study with cardiovascular disease risk, prediction, J. Clin. Med., 8 (2019), p. 1050.
[8]A. H, M.H. Ribeiro, G.M.M. Paixão, et al., Automatic diagnosis of the 12-lead ECG using a deep neural network,Nat. Commun., 11 (2020), p. 1760.
[9]Bhekumuzi M. Mathunjwa, Yin-Tsong Lin, Chien-Hung Lin, ECG recurrence plot-based arrhythmia classification using two-dimensional deep residual CNN features, Sensors, 22 (2022), p. 1660.
[10]Sraitih Mohamed, Younes Jabrane, Amir Hajjam El Hassani, An automated system for ECG arrhythmia detection using machine learning techniques, J. Clin. Med., 10 (2021), p. 5450.
[11]Wusat Ullah, Imran Siddique, Rana Muhammad Zulqarnain, Classification of arrhythmia in heartbeat detection using deep learning, Hindawi , Computational Intelligence and Neuroscience (2021), p. 13. [12]Saira Aziz, Sajid Ahmed, Mohamed-Slim Alouini, ECG-based machine-learning algorithms for heartbeat classification, Sci. Rep., 11 (2021), Article 18738.
[13]Mengze Wu, Yongdi Lu, Wenli Yang and Shen Yuong Wong , “A study on arrhythmia via ECG signal classification using the convolutional neural network “,Front. Comput. Neurosci. 14.
[14]Fajr Ibrahem Alarsan, Mamoon Younes, Analysis and classification of heart diseases using heartbeat features and machine learning algorithms, J. Big Data (2019), 10.1186.
[15] Moradi, M., Fatehi, M., Masoumi, H., Taghizadeh, M. Deep neural network method for classification of sleep stages using spectrogram of signal based on transfer learning with different domain data. Scientia Iranica, 2022; 29(4): 1898-1903.
[16] Moradi, M., Fatehi, M., Masoumi, H., Taghizadeh, M. Deep Learning Method for Sleep Stages Classification by Time-Frequency Image. Signal Processing and Renewable Energy, 2021; 5(3): 67-83.
[17] Moradi MM, Fatehi MH, Masoumi H, Taghizadeh M. Adaptive neuro-fuzzy method for sleep stages detection by PPG signal. Journal of Advanced Pharmacy Education & Research| Jan-Mar. 2020; 10(S1).