تجزیه و تحلیل چندوجهی سیگنال‌های الکتروکاردیوگرام برای تشخیص آریتمی قلبی با بهره‌گیری از روش‌های یادگیری ماشین و یادگیری عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد هوش مصنوعی، گروه مهندسی کامپیوتر، دانشکده فنی و مهندسی، دانشگاه میبد، میبد، ایران

2 استادیار گروه مهندسی کامپیوتر، دانشکده فنی و مهندسی، دانشگاه میبد، میبد، ایران

3 دانشیار گروه مهندسی کامپیوتر، دانشکده فنی و مهندسی، دانشگاه میبد، میبد، ایران

چکیده

بیماری‌های قلبی مانند آریتمی قلبی شایع‌ترین علت مرگ در جهان محسوب می‌شوند. تشخیص سریع این نوع بیماری باعث افزایش کیفیت زندگی، طول عمر و کاهش هزینه‌های درمان می‌شود. در این پژوهش هدف شناسایی بیماری آریتمی قلبی از روی الکتروکاردیوگرام و ابزار هوش مصنوعی است. روش پیشنهادی از سه مرحله پیش‌پردازش، تقسیم‌بندی پایگاه داده و طبقه‌بندی داده‌ها تشکیل‌شده است. ابتدا در مرحله پیش‌پردازش، عملیات نرمال‌سازی، پاک‌سازی و متوازن‌سازی کلاس‌ها انجام شده است. سپس پایگاه داده پردازش‌شده برای عملیات آموزش و آزمایش تقسیم‌بندی شده است. در نهایت داده‌ها با استفاده از طبقه‌بندهای مختلف یادگیری ماشین، معماری‌های یادگیری عمیق و یک مدل ترکیبی از معماری‌های CNN، RNN و Transformer، گروه‌بندی شده‌اند. روش پیشنهادی با پایگاه داده MIT-BIH مورد ارزیابی قرار گرفته است. نتایج ارزیابی‌ها نشان داد که از بین مدل‌های یادگیری ماشین و معماری‌های مختلف یادگیری عمیق، مدل ترکیبی با ادغام ویژگی‌های محلی حاصل از معماری CNN و شناسایی وابستگی‌های زمانی طولانی و پیچیده توسط معماری RNN و Transformer جز برترین طبقه‌بندها هست. در نهایت، یافته‌ها بر اهمیت ادغام ویژگی‌های چندگانه در تحلیل سیگنال‌های حاصل از الکتروکاردیوگرام برای تشخیص دقیق‌تر آریتمی قلبی تأکید می‌کند و می‌تواند در توسعه سیستم‌های تشخیصی خودکار کارآمدتر استفاده شود.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Multimodal analysis of ECG signals for cardiac arrhythmia detection using machine learning and deep learning methods

نویسندگان [English]

  • Motahareh Akbari Podineh 1
  • Fatemeh Zare Mehrjardi 2
  • Mohsen Sardari Zarchi 3
1 MSc. in Artificial Intelligence, Computer Engineering Department, Faculty of Technology and Engineering, Meybod University, Meybod, Yazd, Iran
2 Assistant Professor, Computer Engineering Department, Faculty of Technology and Engineering, Meybod University, Meybod, Yazd, Iran
3 Associate Professor, Computer Engineering Department, Faculty of Technology and Engineering, Meybod University, Meybod, Yazd, Iran
چکیده [English]

Cardiovascular diseases, such as cardiac arrhythmia, are considered the most common cause of death worldwide. Early detection of this type of heart disease increases patient quality of life, prolongs life, and reduces treatment costs. In this research, the goal is to identify cardiac arrhythmia from electrocardiogram using artificial intelligence tools. The proposed method consists of three stages: preprocessing, database partitioning, and data classification. First, in the preprocessing stage, operations such as data normalization, cleaning, and balancing of classes have been performed. Then, the processed database has been partitioned for training and testing operations. Finally, the data has been classified using various machine learning classifiers, deep learning architectures, and a hybrid model combining CNN, RNN, and Transformer architectures. The proposed method has been evaluated using the MIT-BIH database. Evaluation results showed that among machine learning models and various deep learning architectures, the hybrid model, by integrating local features obtained from the CNN architecture and identifying long and complex temporal dependencies by the RNN and Transformer architectures, is among the top classifiers. Ultimately, the findings emphasize the importance of integrating multiple features in ECG signal analysis for more accurate cardiac arrhythmia diagnosis and can be used in the development of more efficient automated diagnostic systems.

کلیدواژه‌ها [English]

  • Cardiac arrhythmia
  • ECG signal
  • machine learning
  • deep learning

مراجع

[1]     D. G. Manuel, M. Leung, K. Nguyen, P. Tanuseputro and H. Johansen, “Burden of cardiovascular disease in Canada,” Canadian Journal of Cardiology, Vol. 19, No. 9, pp. 997-1004, 2003.
[2]     S. Setayesh and M. A. Tabrazed, “Predicting Heart Attack by Detecting Abnormalities in ECG Data Using Deep Self-Encoding Network”, National Conference on Artificial Intelligence and Software Engineering, 1402, pp. 1-6.
[3]     F. Z. Mehrjardi, A. M. Latif, M. S. Zarchi, and R. Sheikhpour, “A survey on deep learning-based image forgery detection,” Pattern Recognition, vol. 144, 2024, doi: 10.1016/j.patcog.2023.109778.
[4]     F. Z. Mehrjardi, A. M. Latif, and M. S. Zarchi, "Copy-move forgery detection and localization using deep learning," International Journal of Pattern Recognition and Artificial Intelligence, Vol. 37, No. 9, 2023, doi: 10.1142/S0218001423520122.
[5]     B. Wang, X. Lyu, J. Qu, H. Sun, Z. Pan and Z. Tang, “GNDD: A graph neural network-based method for drug-disease association prediction,” In IEEE International Conference on Bioinformatics and Biomedicine (BIBM),  pp. 1253-1255, IEEE, 2019, doi: 10.1109/BIBM47256.2019.8983257.
[6]     U. R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan and M. Adam, “Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals,” Information sciences, Vol. 415, pp. 190-198, 2017, doi: 10.1016/j.ins.2017.06.027.
[7]     M. Vijayagopal, S. Muralidhara, N. Kashyap and P. Mendiratta, “Arrhythmia prediction and diagnosis using data analysis,” NC State University, Raleigh, 2020.
[8]     F. Murat, O. Yildirim, M. Talo, Y. Demir, R. S. Tan, E. J. Ciaccio, and U. R. Acharya, “Exploring deep features and ECG attributes to detect cardiac rhythm classes,” Knowledge-Based Systems, Vol. 232, 2021, doi: 10.1016/j.knosys.2021.107473.
[9]     H. V. Denysyuk, R. J. Pinto, P. M. Silva, R. P. Duarte, F. A. Marinho, L. Pimenta and I.M. Pires, “Algorithms for automated diagnosis of cardiovascular diseases based on ECG data: A comprehensive systematic review,” Vol. 9, No. 2, 2023, 10.1016/j.heliyon.2023.e13601.
[10] S. Sahoo, M. Dash, S. Behera and S. Sabut, “Machine learning approach to detect cardiac arrhythmias in ECG signals: A survey,” Vol. 41, No. 4, pp.185-194, 2020, doi: 10.1016/j.irbm.2019.12.001.
[11] C. Li, H. Zhao, W. Lu, X. Leng, L. Wang, X. Lin, and J. Xiang, “DeepECG: Image-based electrocardiogram interpretation with deep convolutional neural networks,” Biomedical Signal Processing and Control, Vol. 69, 2021, doi: 10.1016/j.bspc.2021.102824.
[12] S. Sattar, R. Mumtaz, M. Qadir, S. Mumtaz, M. A. Khan, T. De Waele and A. Shahid, “Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets,” Sensors, Vol. 24, No. 8, 2024, doi: 10.3390/s24082484
[13] M. A. Raza, M. Anwar, K. Nisar, A. A. A. Ibrahim, U. A. Raza, S. A. Khan, F. Ahmad “Classification of electrocardiogram signals for arrhythmia detection using convolutional neural network,” Computers, Materials and Continua,Vol.77, No. 3, pp. 3817-3834, 2023.
[14] Z. F. M. Apandi, R. Ikeura and S. Hayakawa, “Arrhythmia detection using MIT-BIH dataset: A review,” In International Conference on Computational Approach in Smart Systems Design and Applications (ICASSDA), pp. 1-5, 2018, doi: 10.1109/ICASSDA.2018.8477620.
[15] J. Z. Ahmadabadi, F. Z. Mehrjardi, M. Ghanbary and M. Mirzaei, “Identification of Effective Factors and Prediction of Ischemic Heart Disease Using Machine Learning Methods and Data from the Yazd Health Study (YaHS),” Journal of Shahid Sadoughi University of Medical Sciences, Vol. 32, No. 7, pp. 67-79, 2024, doi:  10.18502/ssu.v32i7.16571.
[16] F. Rustam, M. Khalid, W. Aslam, V. Rupapara, A. Mehmood and G.S. Choi, “A performance comparison of supervised machine learning models for Covid-19 tweets sentiment analysis,” Plos one, Vol. 16, No. 2, 2021, doi: 10.1371/journal.pone.0245909.
[17] S. Ray, “A quick review of machine learning algorithms,” In International conference on machine learning, big data, cloud and parallel computing (COMITCon), pp. 35-39, 2019, doi: 10.1109/COMITCon.2019.8862451.
[18] H, Jafarzadeh, M. Mahdianpari, E. Gill, F. Mohammadimanesh and S. Homayouni, “Bagging and boosting ensemble classifiers for classification of multispectral, hyperspectral and PolSAR data: a comparative evaluation,” Remote Sensing, Vol. 13, No. 21, 2021, doi: 10.3390/rs13214405.
[19] B. Mahesh, “Machine learning algorithms-a review,” International Journal of Science and Research (IJSR), Vol. 9, No. 1, pp. 381-386, 2020, doi: 10.21275/ART20203995.
[20] S. M. Matinkhah, A. khakbaz, F. Adibnia, “Application of 'long-term-short-term memory' and 'convolutional neural networks' to detect distributed denial of service attacks,” Applied and Basic Machine Intelligence Research, Vol. 2, No. 1, 2024, doi: 10.22034/ABMIR.2023.19764.1025.
[21] A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez and I. Polosukhin, “Attention is all you need,” Advances in neural information processing systems, Vol. 30, 2017.
[22] T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” arXiv preprint arXiv:1609.02907, 2016, doi: 10.48550/arXiv.1609.02907.
[23] D. Oniani, C. Wang, Y. Zhao, A. Wen, H. Liu and F. Shen, “Comparisons of graph neural networks on cancer classification leveraging a joint of phenotypic and genetic features,” arXiv preprint arXiv:2101.05866, 2021.
[24] M. Chourasia, A. Thakur, S. Gupta and A. Singh, “ECG heartbeat classification using CNN,” In IEEE 7th Uttar Pradesh Section International Conference on Electrical, Electronics and Computer Engineering (UPCON), pp. 1-6, IEEE, 2020, doi:  10.1109/UPCON50219.2020.9376451
[25] A. A. Ahmed, W. Ali, T. A. Abdullah and S. J. Malebary, “Classifying cardiac arrhythmia from ECG signal using 1D CNN deep learning model,” Mathematics, Vol. 11, No. 3, pp. 1-16, 2023, doi: 10.3390/math11030562.
[26] C. G. Igiri, V. I. E. Anireh, N. D. Nwiabu, and D. Matthias, "Comparative analysis of supervised machine learning algorithms for ECG arrhythmia detection using small dataset," International Journal of Computer Science and Mathematical Theory (IJCSMT), vol. 9, no. 4, pp. 23–44, 2023.
[27] N. Pant, P. Singh, and R. Bera, "ECG-GraphNet: A graph neural network approach for electrocardiogram-based arrhythmia classification," Biomedical Signal Processing and Control, vol. 87, 105442, 2024.
[28] M. S. Al Rahhal, Y. Bazi and H. AlHichri, "Deep learning approach for active classification of electrocardiogram signals," Journal of Medical Systems, vol. 44, no. 4, pp. 1–11, 2020.
[29] H. Shi, H. Xu and M. Zhou,"Transformer-based anomaly detection for ECG signals," Algorithms, vol. 16, no. 4, 185, MDPI, 2023.
پژوهش های نظری و کاربردی هوش ماشینی
دوره 3، شماره 1
شهریور 1404
صفحه 17-34

فایل ها

هم رسانی

ارجاع به این مقاله

آمار