Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network_Journal of Biomedical Engineering

Authors：

CHA Xingzeng ¹ , ZHANG Yue ¹ , ZHANG Yifei ¹ , SU Ye ² ,  LAI Dakun ¹

1. School of Electronic Science and Engineering, University of Electronic Science and technology, Chengdu 610054, P. R. China;
2. Department of Cardiovascular Ultrasound and Cardiology, Sichuan Academy of Medical Sciences & Sichuan Provincial People's Hospital, Chengdu 610072, P. R. China;

Corresponding author：

LAI Dakun, Email: dklai@uestc.edu.cn

Keywords：

Sudden cardiac arrest; Electrocardiogram; Heart rate features; Rapid response systems; Deep transfer learning.

DOI：

10.7507/1001-5515.202306066

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Sudden cardiac arrest (SCA) is a lethal cardiac arrhythmia that poses a serious threat to human life and health. However, clinical records of sudden cardiac death (SCD) electrocardiogram (ECG) data are extremely limited. This paper proposes an early prediction and classification algorithm for SCA based on deep transfer learning. With limited ECG data, it extracts heart rate variability features before the onset of SCA and utilizes a lightweight convolutional neural network model for pre-training and fine-tuning in two stages of deep transfer learning. This achieves early classification, recognition and prediction of high-risk ECG signals for SCA by neural network models. Based on 16 788 30-second heart rate feature segments from 20 SCA patients and 18 sinus rhythm patients in the international publicly available ECG database, the algorithm performance evaluation through ten-fold cross-validation shows that the average accuracy (Acc), sensitivity (Sen), and specificity (Spe) for predicting the onset of SCA in the 30 minutes prior to the event are 91.79%, 87.00%, and 96.63%, respectively. The average estimation accuracy for different patients reaches 96.58%. Compared to traditional machine learning algorithms reported in existing literatures, the method proposed in this paper helps address the requirement of large training datasets for deep learning models and enables early and accurate detection and identification of high-risk ECG signs before the onset of SCA.

Citation： CHA Xingzeng, ZHANG Yue, ZHANG Yifei, SU Ye, LAI Dakun. Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network. Journal of Biomedical Engineering, 2024, 41(4): 692-699. doi: 10.7507/1001-5515.202306066 Copy

1.	Chugh S S, Reinier K, Uy-Evanado A, et al. Prediction of sudden cardiac death manifesting with documented ventricular fibrillation or pulseless ventricular tachycardia, JACC Clinical Electrophysiology, 2022, 8(4): 411-423.
2.	Loria-Romero M, Peregrina-Barreto H, Rangel-Magdaleno J, et al. Ventricular fibrillation characterization for sudden cardiac death risk prediction based on wavelet analysis//2022 IEEE International Symposium on Medical Measurements and Applications (MEMEA 2022), Messina, Italy: IEEE, 2022: 1-6.
3.	Sun L, Wang Y, Qu Z, et al. BeatClass: a sustainable ECG classification system in IoT-based eHealth, IEEE Internet of Things Journal, 2022, 9(10): 7178-7195.
4.	Holmstrom L, Zhang F Z, Ouyang D, et al. Artificial intelligence in ventricular arrhythmias and sudden death. Arrhythmia & Electrophysiology Review, 2023, 12: e17.
5.	Aziz H M, Zarzecki M P, Garcia-Zamora S, et al. Pathogenesis and management of brugada syndrome: recent advances and protocol for umbrella reviews of meta-analyses in major arrhythmic events risk stratification, Journal of Clinical Medicine, 2022, 11(7): 1912.
6.	Holmstrom L, Chugh H, Uy-Evanado A, et al. Temporal trends in incidence and survival from sudden cardiac arrest manifesting with shockable and nonshockable rhythms: a 16-year prospective study in a large US Community. Ann Emerg Med, 2023, 82(4): 463-471.
7.	Reinier K, Dizon B, Chugh H, et al. Warning symptoms associated with imminent sudden cardiac arrest: a population-based case-control study with external validation. Lancet Digit Health, 2023, 5(11): e763-e773.
8.	Yu P, Skinner M, Esangbedo I, et al. Predicting cardiac arrest in children with heart disease: a novel machine learning algorithm. J Clin Med, 2023, 12(7): 2728.
9.	Chae M, Gil H W, Cho N J, et al. Machine learning-based cardiac arrest prediction for early warning system. Mathematics, 2022, 10(12): 2049.
10.	Alves Pinto R, Proença T, Martins Carvalho M, et al. Long-term prognosis of out-of-hospital cardiac arrest due to idiopathic ventricular arrhythmias. Monaldi Arch Chest Dis, 2023, 93(4). DOI: 10.4081/monaldi.2023.2501.
11.	Lee Y J, Cho K J, Kwon O, et al. A multicentre validation study of the deep learning-based early warning score for predicting in-hospital cardiac arrest in patients admitted to general wards. Resuscitation, 2021, 163: 78-85.
12.	Shridharani A R, Parasuram H, Balaraman M, et al. Retrospective analysis of autonomic dysfunction in epilepsy patients from neurophysiological recordings. Neurology ASIA, 2022, 27: 649-661.
13.	Park E J. Association between vitamin B12 status and heart rate variability in patients with ischemic stroke. Medicine (Baltimore), 2023, 102(16): e33428.
14.	Pizarro C, Bosse F L, Begrich C, et al. Cardiac autonomic dysfunction in adult congenital heart disease. BMC Cardiovasc Disord, 2023, 23(1): 513.
15.	Murugappan M, Murugesan L, Jerritta S, et al. Sudden cardiac arrest (SCA) prediction using ECG morphological features. Arabian Journal for Science and Engineering, 2021, 46: 947-961.
16.	Pham V S, Nguyen A, Dang H B, et al. Diagnosis of sudden cardiac arrest using principal component analysis in automated external defibrillators. Sci Rep, 2023, 13(1): 8768.
17.	Singhal A, Agarwal M. An automatic risk assessment system for sudden cardiac death using look ahead pattern. Multimedia Tools and Applications, 2023, 83: 27243-27258.
18.	Taye G T, Hwang H J, Lim K M. Application of a convolutional neural network for predicting the occurrence of ventricular tachyarrhythmia using heart rate variability features. Sci Rep, 2020, 10(1): 6769.
19.	Acharya U R, Fujita H, Sudarshan V K, et al. Automated prediction of sudden cardiac death risk using kolmogorov complexity and recurrence quantification analysis features extracted from HRV signals//2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015): Big Data Analytics for Human-Centric Systems, 2015: 1110-1115.
20.	Houshyarifar V, Chehel Amirani M. An approach to predict sudden cardiac death (SCD) using time domain and bispectrum features from HRV signal. Biomed Mater Eng, 2016, 27(2-3): 275-285.
21.	Ebrahimzadeh E, Manuchehri M S, Amoozegar S, et al. A time local subset feature selection for prediction of sudden cardiac death from ECG signal. Med Biol Eng Comput, 2018, 56(7): 1253-1270.
22.	Ebrahimzadeh E, Foroutan A, Shams M, et al. An optimal strategy for prediction of sudden cardiac death through a pioneering feature-selection approach from HRV signal. Comput Methods Programs Biomed, 2019, 169: 19-36.
23.	Velazquez-Gonzalez J R, Peregrina-Barreto H, Rangel-Magdaleno J J, et al. ECG-based identification of sudden cardiac death through sparse representations. Sensors (Basel), 2021, 21(22): 7666.
24.	Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
25.	Kim J Y, Park Y J, Park K M, et al. Non-invasive risk assessment and prediction of mortality in patients undergoing coronary artery bypass graft surgery. J Cardiovasc Dev Dis, 2023, 10(9): 365.
26.	Neri L, Oberdier M T, Augello A, et al. Algorithm for mobile platform-based real-time QRS detection. Sensors (Basel), 2023, 23(3): 1625.

1. Chugh S S, Reinier K, Uy-Evanado A, et al. Prediction of sudden cardiac death manifesting with documented ventricular fibrillation or pulseless ventricular tachycardia, JACC Clinical Electrophysiology, 2022, 8(4): 411-423.
2. Loria-Romero M, Peregrina-Barreto H, Rangel-Magdaleno J, et al. Ventricular fibrillation characterization for sudden cardiac death risk prediction based on wavelet analysis//2022 IEEE International Symposium on Medical Measurements and Applications (MEMEA 2022), Messina, Italy: IEEE, 2022: 1-6.
3. Sun L, Wang Y, Qu Z, et al. BeatClass: a sustainable ECG classification system in IoT-based eHealth, IEEE Internet of Things Journal, 2022, 9(10): 7178-7195.
4. Holmstrom L, Zhang F Z, Ouyang D, et al. Artificial intelligence in ventricular arrhythmias and sudden death. Arrhythmia & Electrophysiology Review, 2023, 12: e17.
5. Aziz H M, Zarzecki M P, Garcia-Zamora S, et al. Pathogenesis and management of brugada syndrome: recent advances and protocol for umbrella reviews of meta-analyses in major arrhythmic events risk stratification, Journal of Clinical Medicine, 2022, 11(7): 1912.
6. Holmstrom L, Chugh H, Uy-Evanado A, et al. Temporal trends in incidence and survival from sudden cardiac arrest manifesting with shockable and nonshockable rhythms: a 16-year prospective study in a large US Community. Ann Emerg Med, 2023, 82(4): 463-471.
7. Reinier K, Dizon B, Chugh H, et al. Warning symptoms associated with imminent sudden cardiac arrest: a population-based case-control study with external validation. Lancet Digit Health, 2023, 5(11): e763-e773.
8. Yu P, Skinner M, Esangbedo I, et al. Predicting cardiac arrest in children with heart disease: a novel machine learning algorithm. J Clin Med, 2023, 12(7): 2728.
9. Chae M, Gil H W, Cho N J, et al. Machine learning-based cardiac arrest prediction for early warning system. Mathematics, 2022, 10(12): 2049.
10. Alves Pinto R, Proença T, Martins Carvalho M, et al. Long-term prognosis of out-of-hospital cardiac arrest due to idiopathic ventricular arrhythmias. Monaldi Arch Chest Dis, 2023, 93(4). DOI: 10.4081/monaldi.2023.2501.
11. Lee Y J, Cho K J, Kwon O, et al. A multicentre validation study of the deep learning-based early warning score for predicting in-hospital cardiac arrest in patients admitted to general wards. Resuscitation, 2021, 163: 78-85.
12. Shridharani A R, Parasuram H, Balaraman M, et al. Retrospective analysis of autonomic dysfunction in epilepsy patients from neurophysiological recordings. Neurology ASIA, 2022, 27: 649-661.
13. Park E J. Association between vitamin B12 status and heart rate variability in patients with ischemic stroke. Medicine (Baltimore), 2023, 102(16): e33428.
14. Pizarro C, Bosse F L, Begrich C, et al. Cardiac autonomic dysfunction in adult congenital heart disease. BMC Cardiovasc Disord, 2023, 23(1): 513.
15. Murugappan M, Murugesan L, Jerritta S, et al. Sudden cardiac arrest (SCA) prediction using ECG morphological features. Arabian Journal for Science and Engineering, 2021, 46: 947-961.
16. Pham V S, Nguyen A, Dang H B, et al. Diagnosis of sudden cardiac arrest using principal component analysis in automated external defibrillators. Sci Rep, 2023, 13(1): 8768.
17. Singhal A, Agarwal M. An automatic risk assessment system for sudden cardiac death using look ahead pattern. Multimedia Tools and Applications, 2023, 83: 27243-27258.
18. Taye G T, Hwang H J, Lim K M. Application of a convolutional neural network for predicting the occurrence of ventricular tachyarrhythmia using heart rate variability features. Sci Rep, 2020, 10(1): 6769.
19. Acharya U R, Fujita H, Sudarshan V K, et al. Automated prediction of sudden cardiac death risk using kolmogorov complexity and recurrence quantification analysis features extracted from HRV signals//2015 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2015): Big Data Analytics for Human-Centric Systems, 2015: 1110-1115.
20. Houshyarifar V, Chehel Amirani M. An approach to predict sudden cardiac death (SCD) using time domain and bispectrum features from HRV signal. Biomed Mater Eng, 2016, 27(2-3): 275-285.
21. Ebrahimzadeh E, Manuchehri M S, Amoozegar S, et al. A time local subset feature selection for prediction of sudden cardiac death from ECG signal. Med Biol Eng Comput, 2018, 56(7): 1253-1270.
22. Ebrahimzadeh E, Foroutan A, Shams M, et al. An optimal strategy for prediction of sudden cardiac death through a pioneering feature-selection approach from HRV signal. Comput Methods Programs Biomed, 2019, 169: 19-36.
23. Velazquez-Gonzalez J R, Peregrina-Barreto H, Rangel-Magdaleno J J, et al. ECG-based identification of sudden cardiac death through sparse representations. Sensors (Basel), 2021, 21(22): 7666.
24. Goldberger A L, Amaral L A, Glass L, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation, 2000, 101(23): E215-E220.
25. Kim J Y, Park Y J, Park K M, et al. Non-invasive risk assessment and prediction of mortality in patients undergoing coronary artery bypass graft surgery. J Cardiovasc Dev Dis, 2023, 10(9): 365.
26. Neri L, Oberdier M T, Augello A, et al. Algorithm for mobile platform-based real-time QRS detection. Sensors (Basel), 2023, 23(3): 1625.

Journal of Biomedical Engineering

Early classification and recognition algorithm for sudden cardiac arrest based on limited electrocardiogram data trained with a two-stages convolutional neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content