2024 Vol.7 Aug.N04

• Title: Research on Classification of Cardiovascular Diseases with Neural Network
• Name: Xinxin Xu
• Company: College of Applied Mathematics, Chengdu University of Information Technology,chengdu 610000 China
• Abstract:

  In order to promote the computer-aided diagnosis of clinical arrhythmia, ResNet-LSTM architecture is proposed for the study of arrhythmia classification. For the MIT-BIH arrhythmia database, the study was divided into four steps. Firstly, ECG is denoised by nine-scale wavelet threshold. Secondly, 300 signal points before and after the de-noised data are taken as heartbeat, with peak r as the center. Finally, the ResNet-LSTM model was constructed for classification data training and prediction, and the necessity of LSTM structure for ECG classification was compared. The classification accuracy of this model was 0.981, the precision was, the recall  was, and the F1 score was that this model could be used to assist the clinical diagnosis of arrhythmia.

  
  

• Keyword: arrhythmia; Wavelet threshold denoising; ResNet; LSTM
• DOI: 10.12250/jpciams2024090801
• Citation form: Xinxin Xu.Research on Classification of Cardiovascular Diseases with Neural Network[J]. Computer Informatization and Mechanical System,2024,Vol.7,pp.1-3

[1]Sraitih M ,Jabrane Y ,El Hassani AH .An Automated System for ECG Arrhythmia Detection Using Machine Learning Techniques[J].Journal of Clinical Medicine, 2021,10:22.

[2]Petmezas G , Haris K , Stefanopoulos L ,et al.Automated Atrial Fibrillation Detection using a Hybrid CNN-LSTM Network on Imbalanced ECG Datasets[J].Biomedical signal processing and control, 2021(Jan.):63.

[3]Hammad M ,Alkinani MH ,Gupta BB ,et al.Myocardial infarction detection based on deep neural network on imbalanced data[J].Multmedia Systems,2022,28(4):1373-1385.

[4]Hammad M , Iliyasu A M , Subasi A ,et al.A Multitier Deep Learning Model for Arrhythmia Detection[J].IEEE Transactions on Instrumentation and Measurement, 2021,(70-):70.

[5]Hamil H , Zidelmal Z , Azzaz M S ,et al.Design of a secured telehealth system based on multiple biosignals diagnosis and classification for IoT application[J].Expert Systems.

[6] Afkhami, R. G., Azarnia, G., and Tinati, M. A. (2016). Cardiac arrhythmia classification using statistical and mixture modeling features of ECG signals. Pattern Recognition Letters, 70, 45-51.

[7]  Garcia, G., Moreira, G., Luz, E., and Menotti, D. (July 2016). Improving automatic cardiac arrhythmia classification: Joining temporal-VGC, complex networks and SVM classifier. In 2016 International Joint Conference on Neural Networks (IJCNN) (pp. 3896-3900). IEEE.

[8] Xu, X., Jeong, S., & Li, J. (2020). Interpretation of Electrocardiogram (ECG) Rhythm by Combined CNN and BiLSTM. IEEE Access, 8, 125380-125388.

[9] Yu Yan, Yan Song-Song, Qiu Lei et al. Arrhythmia classification based on deep neural networks [J]. Automation Technology and Application,2023,42(08):1-5. (in Chinese) DOI:10.20033/ J.1003-7241.(2023)08-0001-05.

[10]Pandey S K,Janghel R R,Vani V. Patient-specific machine learning models for ECG signal classification. Procedia Computer Science, 2020, 167: 2181-2190.

[11]Chen C,Hua Z,Zhang R,et al. Automated arrhythmia classification based on a combination network of CNN and LSTM. Biomed Signal Proces Control, 2020, 57: 101819.

[12]Malleswari, P. N., Bindu, C. H., & Prasad, K. S. (2021). Cardiac Severity Classification Using Pre-Trained Neural Networks. Interdisciplinary Sciences: Computational Life Sciences, 13(3), 443–450.

[13]Hao, S., Xu, H., Ji, H., Wang, Z., Zhao, L., Ji, Z., & Ganchev, I. (2023). G2-ResNeXt: a novel model for ECG signal classification. IEEE Access.

[14]Kuila S, Dhanda N, Joardar S. ECG signal classification and arrhythmia detection using ELM-RNN[J]. Multimedia Tools and Applications, 2022, 81(18): 25233-25249.