A Hybrid Deep Learning Approach for ECG Arrhythmia Detection: GPT, GANs, and Triplet Loss Integration | [International Journal of Communication Networks and Information Security • 2024]

Author(s):

1. Sultan faiz alqurashi: Saudi Red Crescent Authority, Saudi Arabia

2. Yasser Mefreej Alahmadi: Saudi Red Crescent Authority, Saudi Arabia

3. Abdulrahman mohammed alsherbi: Saudi Red Crescent Authority, Saudi Arabia

4. Eid Ayed Alosaimi: Saudi Red Crescent Authority, Saudi Arabia

5. Fawaz Matuq Almuwallad: Saudi Red Crescent Authority, Saudi Arabia

6. Abdulmajeed Abdullah Alswat: Saudi Red Crescent Authority, Saudi Arabia

7. Abdulaziz selmi alsaedi: Saudi Red Crescent Authority, Saudi Arabia

8. Sameer mubarak alqurashi: Saudi Red Crescent Authority, Saudi Arabia

9. Mohammed Abdullah Alharthi: Saudi Red Crescent Authority, Saudi Arabia

10. Mohsen hassan alsrori: Saudi Red Crescent Authority, Saudi Arabia

11. Ghorm Ahmad Alghamdi,: Saudi Red Crescent Authority, Saudi Arabia

12. Khalid Owidh Alotibi: Saudi Red Crescent Authority, Saudi Arabia

13. Faisal nawar althobaiti: Saudi Red Crescent Authority, Saudi Arabia

Abstract:

This paper proposes a novel deep-learning method to detect arrhythmias from the ECG data by adopting pre-trained GPT models and other powerful state-of-the-art DL algorithms. Most traditional ECG classification models face challenges in capturing complex temporal dependencies and handling class imbalances. To meet these challenges, our system leverages GPT to capture complex temporal patterns and contextual relationships within ECG signals, enabling us to better under-stand the more intricate depen-dencies in the data. Finally, the proposed system lever-ages data augmentation with Generative Adversarial Networks (GANs) to generate a wide variety ofcomplex samples, which help improve model capability and robustness. It also uses Triplet Loss, which shows it can work better on imbalanced classes and tiny differencesin different cardiac arrhythmias. Compared with other methods, our results exhibit great im-provements in classification performance, particularly for rare arrhythmias. Model Interpretability is based on SHapley Additive exPlanations(SHAP) and Gradient weighted Class Activation Map (Grad-CAM), which interpret the model decisions.

Page(s): 858-877

DOI: DOI not available

Published: Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 4, Year: 2024

Keywords:

GPT , GANs , Arrhythmia Detection , Triplet Loss , Model Interpretability , ECG Classification

References:

[1] Aggarwal and Yang,Wei and Yang .2021 ."Non-invasive fetal electrocardiogram monitoring techniques: Potential and future research opportunities in smart textiles. " Signals, 2(3) : 392-412.

[2] Fu .2015 .Du-guan. "Cardiac arrhythmias: diagnosis, symptoms, and treatments." Cell biochemistry and biophysics 73, no. , (2) : 291-296.

[3] Merdjanovska Aleksandra,Rashkovska Aleksandra .2022 ."Comprehensive survey of computational ECG analysis: Databases, methods and applications. " Expert Systems with Applications, 203 : 117206.

[4] Ansari Erchin,Serpedin Erchin .2023 ."Deep learning for ECG Arrhythmia detection and classification: an overview of progress for period 2017-2023." Frontiers in Physiology 14 (. , : 1246746.

[5] Ebrahimi Arash,Gharehbaghi Arash .2020 ."A review on deep learning methods for ECG arrhythmia classification." Expert Systems with Applications: X 7 (. , : 100033.

[6] Din Erchin,Serpedin Erchin .2024 ."ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial-temporal and long-range dependency features. " Artificial Intelligence in Medicine, 150 : 102818.

[7] El-Ghaish Emadeldeen,Eldele Emadeldeen .2024 ."ECGTransForm: Empowering adaptive ECG arrhythmia classification framework with bidirectional transformer.". Biomedical Signal Processing and Control, 89 : 105714.

[8] Patwardhan Stefano,Marrone Carlo,Sansone Carlo .2023 ."Transformers in the real world: A survey on nlp applications. " Information, 14(4) : 242.

[9] Shi Jingyuan,Zhao Jingyuan,Zhenghong Wang,Heng Zhao Wang,Junbin Wang,Yubo Lian Andrew F.,Burke Andrew F. .2023 ."Spatial-temporal self-attention transformer networks for battery state of charge estimation. " Electronics, 12 : 2598.

[10] Nagamani S.,Jaikanth S.,Jayakumar V.,Manikandan V. .2023 ."Enhancing Diagnostic Accuracy in Echocardiography with Deep Learning Techniques.". In 2023 3rd International Conference on Innovative Mechanisms for Industry Applications (ICIMIA), : 941-948.

[11] Chen Shen,Zhao Shen,Wei-Shi Zheng Ruixuan,Wang Ruixuan .2023 ."PCCT: Progressive class-center triplet loss for imbalanced medical image classification.". IEEE Journal of Biomedical and Health Informatics, 27(4) : 2026-2036.

[12] Chen ,Tsai-Min ,Yuan-Hong Tsai,Huan-Hsin Tseng,Kai-Chun Liu,Jhih-Yu Chen,Chih-Han Huang,Li GuoYuan,Chun-Yen Shen and Yu,Tsao and Yu .2023 ."Srecg: Ecg signal super-resolution framework for portable/wearable devices in cardiac arrhythmias classification. " IEEE Transactions on Consumer Electronics, 69(3) : 250-260.

[13] Quach ,Luyl-Da .2023 .Khang Quoc Nguyen, Anh Quynh Nguyen, Nguyen Thai-Nghe, and Tri Gia Nguyen. "Explainable Deep Learning Models With Gradient-Weighted Class Activation Mapping for Smart Agriculture." IEEE Access 11, no. August, : 83752-83762.

[14] Dash Junyi,Ye Guiling,Wang Guiling .2023 ."A review of generative adversarial networks (GANs) and its applications in a wide variety of disciplines: from medical to remote sensing. " IEEE Access, : .

[15] Mandal Pulak,Mondal Pulak .2021 ."Detection of Ventricular Arrhythmia by using Heart rate variability signal and ECG beat image. " Biomedical Signal Processing and Control, 68 : 102692.

[16] Mandal Nabanita,Sinha Nabanita .2021 ."Prediction of atrial fibrillation based on nonlinear modeling of heart rate variability signal. SVM classifier." Research on Biomedical Engineering, 37 : 725-736.

[17] Hirsch Søren H.,Jensen Sadasivan,Puthusserypady Sadasivan .2021 ."Atrial fibrillation detection using heart rate variability and atrial activity: A hybrid approach. " Expert Systems with Applications, 169 : 114452.

[18] Khairuddin Adam,Mohd K. N. F. Ku,Azir K. N. F. Ku,Lumpur Kuala .2021 ."Using the HAAR wavelet transform and K-nearest neighbour algorithm to improve ECG detection and classification of arrhythmia.". Part II 34, : 310-322.

[19] Sinha ,Arpita Das .2022 ."ECG beat classification based on discriminative multilevel feature analysis and deep learning approach. " Biomedical Signal Processing and Control, 78 : 103943.

[20] Gajowniczek Chandrajit,Bajaj Chandrajit .2020 ."Weighted random forests to improve arrhythmia classification." Electronics 9. , (1) : 99.

[21] Eltrass ,Mazhar B.,Tayel B.,Abeer I.,Ammar I. .2022 ."Automated ECG multi-class classification system based on combining deep learning features with HRV and ECG measures. " Neural Computing and Applications, 11 : 8755-8775.

[22] Islam Md,Shofiqul Md .2023 .Julian MW Quinn, and Mohammad Ali Moni. "HARDC: A novel ECG-based heartbeat classification method to detect arrhythmia using hierarchical attention based dual structured RNN with dilated CNN.". Neural Networks, 162 : 271-287.

[23] Hammad M.,Iliyasu A.M.,Subasi A.,Ho E.S.L.,El-Latif A.A.A. .2021 .A multitier deep learning model for Arrhythmia detection. IEEE Trans. Instrum. Meas, 70 : 1-9.

[24] Degirmenci Aydin,Akan Aydin .2022 ."Arrhythmic heartbeat classification using 2d convolutional neural networks. " Irbm, 43(5) : 422-433.

[25] Nurmaini S.,Darmawahyuni A.,Mukti A.N. Sakti,Rachmatullah M.N.,Firdaus F.,Tutuko B. .2020 .Deep learningbased stacked denoising and autoencoder for ECG heartbeat classification. Electronics, 9(1) : 135.

[26] Kim Y.K.,Lee M.,Song H.S.,Lee S.-W. .2022 .Automatic cardiac Arrhythmia classification using residual network combined with long short-term memory. IEEE Trans. Instrum. Meas, 71 : 1-17.

[27] Ma ,Algorithms Classification .2022 ."Deep Learning‐Based Data Augmentation and Model Fusion for Automatic Arrhythmia Identification. " Computational Intelligence and Neuroscience, (1) : 1577778.

[28] Pokaprakarn T.,Kitzmiller R.R.,Moorman R.,Lake D.E.,Krishnamurthy A.K.,Kosorok M.R. .2022 .Sequence to sequence ECG cardiac rhythm classification using convolutional recurrent neural networks. IEEE J. Biomed. Health Inf, 26(2) : 572-580.

[29] Jin Y.,Liu Y.,Qin C.,Li Z.,Xiao D.,Zhao L.,Liu C. .2022 .A novel interpretable method based on dual-level attentional deep neural network for actual multilabel Arrhythmia detection. IEEE Trans. Instrum. Meas, 71 : 1-11.

[30] Xia Y.,Xiong Y.,Wang K. .2023 .A transformer model blended with CNN anddenoising autoencoder for interpatient ECG Arrhythmia classification. Biomed. Signal Process. Control, 86 : 105271.

[31] El-Ghaish H.,Eldele E. .2024 .Empowering adaptive ECG arrhythmia classification framework with bidirectional transformer. Biomedical Signal Processing and Control, 89 : 105714.

[32] Meng ,Xiaoxia Yin and Yanchun,Zhang and Yanchun .2022 ."Enhancing dynamic ECG heartbeat classification with lightweight transformer model. " Artificial Intelligence in medicine 124, : 102236.

[33] Hutchins DeLesley,Neyshabur Behnam .2022 ."Block-recurrent transformers. " Advances in neural information processing systems, 35 : 33248-33261.

[34] Omarov Maigul,Zhekambayeva Maigul .2024 ."Ensemble Approach Combining Deep Residual Networks and BiGRU with Attention Mechanism for Classification of Heart Arrhythmias.". Computers, Materials & Continua, 80(1) : .

[35] Huang Hongru,Li and Xia,Yu and Xia .2023 ."A novel time representation input based on deep learning for ECG classification. " Biomedical Signal Processing and Control, 83 : 104628.

[36] Nerella .2024 ."Transformers and large language models in healthcare: A review." Artificial Intelligence in Medicine (. , : 102900.

[37] Xia Yongliang,Zhang Yongliang .2023 ."Generative adversarial network with transformer generator for boosting ECG classification.". Biomedical Signal Processing and Control, 80 : 104276.

[38] Pandey Saroj,Kumar Saroj .2019 ."Automatic detection of arrhythmia from imbalanced ECG database using CNN model with SMOTE." Australasian physical. engineering sciences in medicine 42, no. 4, : 1129-1139.

[39] Golany Kira,Radinsky Kira .2019 ."Pgans: Personalized generative adversarial networks for ecg synthesis to improve patient-specific deep ecg classification.". In Proceedings of the AAAI Conference on Artificial Intelligence, 33(01) : 557-564.

[40] Hazra ,Yung-Cheol Byun .2020 ."SynSigGAN: Generative adversarial networks for synthetic biomedical signal generation. " Biology, 12 : 441.

[41] Zheng .2024 ."A cost-sensitive deep neural network-based prediction model for the mortality in acute myocardial infarction patients with hypertension on imbalanced data.". Frontiers in Cardiovascular Medicine, 11 : 1276608.

[42] Hossain Md,Sazzad Md,John M. Betts Andrew P.,Paplinski Andrew P. .2021 ."Dual focal loss to address class imbalance in semantic segmentation. " Neurocomputing, 462 : 69-87.

[43] Vellido Alfredo. " .2020 .The importance of interpretability and visualization in machine learning for applications in medicine. health care." Neural computing and applications 32, 24 : 18069-18083.

[44] Sahlaoui .2021 ."Predicting and interpreting student performance using ensemble models and shapley additive explanations." IEEE Access 9 (. , : 152688-152703.

[45] Ojha ,Pedro G.,Lind G. .2024 ."Exploring Interpretable AI Methods for ECG Data Classification.". In Proceedings of the 5th ACM Workshop on Intelligent Cross-Data Analysis and Retrieval, : 11-18.

[46] Ayano Y.,Schwenker F.,Dufera B. D.,T. G. Debelee. " B. D.," B. D. .2022 .Interpretable machine learning techniques in ECGbased heart disease classification: a systematic review. Diagnostics, 13(1) : 111.

[47] YENDURI ,Gokul .2024 .Gpt (generative pre-trained transformer)-a comprehensive review on enabling technologies, potential applications, emerging challenges, and future directions. IEEE Access, : .

[48] .2001 .The impact of the MIT-BIH Arrhythmia database. IEEE Eng. Med. Biol. Mag, 20(3) : 45-50.

[49] Bousseljot R.,Kreiseler D.,Schnabel A. .1995 .Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. , : .

[50] Kachuee M.,Fazeli S.,M. S. .2018 .Sarrafzadeh, ECG heartbeat classification: A deep transferable representation. in: IEEE International Conference on Healthcare Informatics, ICHI, : 443-444.

Citations

Downloads

Views