Myocardial Infarction Classification Based on Convolutional Neural Network and Recurrent Neural Network
Source abstract
Abstract
Myocardial infarction is one of the most threatening cardiovascular diseases for human beings. With the rapid development of wearable devices and portable electrocardiogram (ECG) medical devices, it is possible and conceivable to detect and monitor myocardial infarction ECG signals in time. This paper proposed a multi-channel automatic classification algorithm combining a 16-layer convolutional neural network (CNN) and long-short term memory network (LSTM) for I-lead myocardial infarction ECG. The algorithm preprocessed the raw data to first extract the heartbeat segments; then it was trained in the multi-channel CNN and LSTM to automatically learn the acquired features and complete the myocardial infarction ECG classification. We utilized the Physikalisch-Technische Bundesanstalt (PTB) database for algorithm verification, and obtained an accuracy rate of 95.4%, a sensitivity of 98.2%, a specificity of 86.5%, and an F1 score of 96.8%, indicating that the model can achieve good classification performance without complex handcrafted features.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: ECG Monitoring and Analysis · Cardiac Imaging and Diagnostics · Heart Rate Variability and Autonomic Control
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Key Laboratory of Biorheological Science and Technology, Ministry of Education, College of Bioengineering, Chongqing University, Chongqing 400030, China
Key Laboratory for National Defense Science and Technology of Innovation Micro-Nano Devices and System Technology, Chongqing 400030, China
Chongqing Engineering Research Center of Medical Electronics Technology, Chongqing 400030, China
Funding
National Natural Science Foundation of China · Chongqing technological Innovation and Application demonstration Project
References (23)
Show source-provided references
1. Heart Disease and Stroke Statistics’2017 Update: A Report from the American Heart Association10.1161/CIR.0000000000000485 ↗
2. Third Universal Definition of Myocardial Infarction10.1161/CIR.0b013e31826e1058 ↗
3. ECG analysis using multiple instance learning for myocardial infarction detection10.1109/TBME.2012.2213597 ↗
4. Arif, M., Malagore, I.A., and Afsar, F.A. (2012). Detection and localization of myocardial infarction using K-nearest neighbor classifier. J. Med. Syst., 279–289.10.1007/s10916-010-9474-3 ↗
5. Inferior myocardial infarction detection using stationary wavelet transform and machine learning approach10.1007/s11760-017-1146-z ↗
6. A New Pattern Recognition Method for Detection and Localization of Myocardial Infarction Using T-Wave Integral and Total Integral as Extracted Features from One Cycle of ECG Signal10.4236/jbise.2014.710081 ↗
7. Farooq, A., Anwar, S., Awais, M., and Rehman, S. (2017, January 18–20). A deep CNN based multi-class classification of Alzheimer’s disease using MRI. Proceedings of the 2017 IEEE International Conference on Imaging Systems and Techniques (IST), Beijing, China.10.1109/IST.2017.8261460 ↗
8. He, T., and Droppo, J. (2016, January 20–25). Exploiting LSTM structure in deep neural networks for speech recognition. Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China.10.1109/ICASSP.2016.7472718 ↗
9. Yoo, Y., and Baek, J.-G. (2018). A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network. Appl. Sci., 8.10.3390/app8071102 ↗
10. Xiong, Z., Stiles, M., and Zhao, J. (2017, January 24–27). Robust ECG Signal Classification for the Detection of Atrial Fibrillation Using Novel Neural Networks. Proceedings of the 2017 Computing in Cardiology Conference, Rennes, France.10.22489/CinC.2017.066-138 ↗
11. Saadatnejad, S., Oveisi, M., and Hashemi, M. (2018). LSTM-Based ECG Classification for Continuous Monitoring on Personal Wearable Devices. arXiv.
12. Reasat, T., and Shahnaz, C. (2017, January 21–23). Detection of inferior myocardial infarction using shallow convolutional neural networks. Proceedings of the 2017 IEEE Region 10 Humanitarian Technology Conference, Dhaka, Bangladesh.10.1109/R10-HTC.2017.8289058 ↗
13. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals10.1016/j.ins.2017.06.027 ↗
14. Li, X., and Wu, X. (, January September). Long short-term memory based convolutional recurrent neural networks for large vocabulary speech recognition. Proceedings of the Annual Conference of the International Speech Communication Association NTERSPEECH 2015, Dresden, Germany.10.21437/Interspeech.2015-648 ↗
15. PhysioBank, PhysioToolkit, and PhysioNet
16. ECG beat classification using PCA, LDA, ICA and Discrete Wavelet Transform10.1016/j.bspc.2013.01.005 ↗
17. A Real-Time QRS Detection Algorithm
18. Negative T wave in ischemic heart disease: A consensus article10.1111/anec.12193 ↗
19. Linear affine transformations between 3-lead (Frank XYZ leads) vectorcardiogram and 12-lead electrocardiogram signals10.1016/j.jelectrocard.2009.05.007 ↗
20. A vectorcardiogram-based classification system for the detection of Myocardial infarction
21. Ge, D. (2008, January 16–18). Detecting myocardial infraction using VCG leads. Proceedings of the 2008 2nd International Conference on Bioinformatics and Biomedical Engineering, Shanghai, China.10.1109/ICBBE.2008.885 ↗
22. Zewdie, G., and Xiong, M. (2019). Fully Automated Myocardial Infarction Classification using Ordinary Differential Equations. arXiv.
23. Strodthoff, N., and Strodthoff, C. (2019). Detecting and interpreting myocardial infarction using fully convolutional neural networks. Physiol. Meas., 40.10.1088/1361-6579/aaf34d ↗