Automatic detection model of hypertrophic cardiomyopathy based on deep convolutional neural network_Journal of Biomedical Engineering

Authors：

BU Yuxiang ¹ , CHA Xingzeng ¹ , ZHU Jinling ¹ , SU Ye ² ,  LAI Dakun ¹

1. School of Electronic Science and Engineering, University of Electronic Science and Technology of China, 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：

Hypertrophic cardiomyopathy; Deep learning; Single-lead electrocardiogram; Convolutional neural network

DOI：

10.7507/1001-5515.202109046

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

The diagnosis of hypertrophic cardiomyopathy (HCM) is of great significance for the early risk classification of sudden cardiac death and the screening of family genetic diseases. This research proposed a HCM automatic detection method based on convolution neural network (CNN) model, using single-lead electrocardiogram (ECG) signal as the research object. Firstly, the R-wave peak locations of single-lead ECG signal were determined, followed by the ECG signal segmentation and resample in units of heart beats, then a CNN model was built to automatically extract the deep features in the ECG signal and perform automatic classification and HCM detection. The experimental data is derived from 108 ECG records extracted from three public databases provided by PhysioNet, the database established in this research consists of 14,459 heartbeats, and each heartbeat contains 128 sampling points. The results revealed that the optimized CNN model could effectively detect HCM, the accuracy, sensitivity and specificity were 95.98%, 98.03% and 95.79% respectively. In this research, the deep learning method was introduced for the analysis of single-lead ECG of HCM patients, which could not only overcome the technical limitations of conventional detection methods based on multi-lead ECG, but also has important application value for assisting doctor in fast and convenient large-scale HCM preliminary screening.

Citation： BU Yuxiang, CHA Xingzeng, ZHU Jinling, SU Ye, LAI Dakun. Automatic detection model of hypertrophic cardiomyopathy based on deep convolutional neural network. Journal of Biomedical Engineering, 2022, 39(2): 285-292. doi: 10.7507/1001-5515.202109046 Copy

1.	Maron B J, Gardin J M, Flack J M, et al. Prevalence of hypertrophic cardiomyopathy in a general population of young adults. Echocardiographic analysis of 4111 subjects in the cardia study. Coronary artery risk development in (young) adults. Circulation, 1995, 92(4): 785-789.
2.	Semsarian C, Ingles J, Maron M S, et al. New perspectives on the prevalence of hypertrophic cardiomyopathy. J Am Coll Cardiol, 2015, 65(12): 1249-1254.
3.	Corrado D, Pelliccia A, Heidbuchel H, et al. Recommendations for interpretation of 12-lead electrocardiogram in the athlete. Eur Heart J, 2010, 31(2): 243-259.
4.	Uberoi A, Stein R, Perez M V, et al. Interpretation of the electrocardiogram of young athletes. Circulation, 2011, 124(6): 746-757.
5.	Drezner J A, Ackerman M J, Anderson J, et al. Electrocardiographic interpretation in athletes: The ‘Seattle criteria’. Br J Sports Med, 2013, 47(3): 122-124.
6.	Maron B J, Haas T S, Murphy C J, et al. Incidence and causes of sudden death in us college athletes. J Am Coll Cardiol, 2014, 63(16): 1636-1643.
7.	丁士骜, 梅举, 丁芳宝, 等. 肥厚梗阻型心肌病合并重度二尖瓣反流的外科治疗策略. 中国胸心血管外科临床杂志, 2016, 23(7): 675-678.
8.	张妙贤. 超声心动图诊断肥厚型心肌病(HCM)的价值. 中国疗养医学, 2017(11): 60-61.
9.	Ripley D P, Musa T A, Dobson L E, et al. Cardiovascular magnetic resonance imaging: What the general cardiologist should know. Heart, 2016, 102(19): 1589-1603.
10.	Dominguez F, Gonzalez-Lopez E, Padron-Barthe L, et al. Role of echocardiography in the diagnosis and management of hypertrophic cardiomyopathy. Heart, 2018, 104(3): 260-272.
11.	Inciardi R M, Galderisi M, Nistri S, et al. Echocardiographic advances in hypertrophic cardiomyopathy: Three-dimensional and strain imaging echocardiography. Echocardiography, 2018, 35(5): 716-726.
12.	Losi M A, Imbriaco M, Canciello G, et al. Left ventricular mass in hypertrophic cardiomyopathy assessed by 2d-echocardiography: Validation with magnetic resonance imaging. J Cardiovasc Transl Res, 2020, 13(2): 238-244.
13.	McLeod C J, Ackerman M J, Nishimura R A, et al. Outcome of patients with hypertrophic cardiomyopathy and a normal electrocardiogram. J Am Coll Cardiol, 2009, 54(3): 229-233.
14.	Fujii J, Saihara S, Sawada H, et al. Distribution of left ventricular hypertrophy and electrocardiographic findings in patient with so-called apical hypertrophic cardiomyopathy. J Cardiogr Suppl, 1985, 6(6): 23-33.
15.	Parisi R, Mirabella F, Secco G G, et al. Multimodality imaging in apical hypertrophic cardiomyopathy. World J Cardiol, 2014, 6(9): 916-923.
16.	Ouyang N, Yamauchi K. Using a neural network to diagnose the hypertrophic portions of hypertrophic cardiomyopathy. MD Computing, 1998, 15(2): 106-109.
17.	Rahman Q A, Tereshchenko L G, Kongkatong M, et al. Utilizing ECG-based heartbeat classification for hypertrophic cardiomyopathy identification. IEEE Trans Nanobioscience, 2015, 14(5): 505-512.
18.	Campbell M J, Zhou X, Han C, et al. Pilot study analyzing automated ECG screening of hypertrophic cardiomyopathy. Heart Rhythm, 2017, 14(6): 848-852.
19.	Lyon A, Ariga R, Minchole A, et al. Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers. Front Physiol, 2018, 9: 213.
20.	马志玲, 邵虹, 胡海霞, 等. 肥厚型心肌病体表心电图特征. 心脏杂志, 2018, 30(5): 532-537.
21.	Acharya U R, Fujita H, Lih O S, et al. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inform Sciences, 2017, 405(1): 81-90.
22.	Lai D K, Bu Y X, Su Y, et al. Non-standardized patch-based ECG lead together with deep learning based algorithm for automatic screening of atrial fibrillation. IEEE J Biomed Health Inform, 2020, 24(6): 1569-1578.
23.	Hannun A Y, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 2019, 25(1): 65-69.
24.	Lai D K, Bu Y X, Su Y, et al. A flexible multilayered dry electrode and assembly to single-lead ECG patch to monitor atrial fibrillation in a real-life scenario. IEEE Sens J, 2020, 20(20): 12295-12306.
25.	Bu Y X, Hassan M F U, Lai D K. The embedding of flexible conductive silver-coated electrodes into ECG monitoring garment for minimizing motion artefacts. IEEE Sens J, 2021, 21(13): 14454-14465.
26.	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.
27.	Bousseljot R, Kreiseler D, Schnabel A. Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik, 1995, 40(S1): 317-318.
28.	Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE T Nucl Sci, 1997, 44(3): 1464-1468.
29.	Rowin E J, Maron B J, Appelbaum E, et al. Significance of false negative electrocardiograms in preparticipation screening of athletes for hypertrophic cardiomyopathy. Am J Cardiol, 2012, 110(7): 1027-1032.

1. Maron B J, Gardin J M, Flack J M, et al. Prevalence of hypertrophic cardiomyopathy in a general population of young adults. Echocardiographic analysis of 4111 subjects in the cardia study. Coronary artery risk development in (young) adults. Circulation, 1995, 92(4): 785-789.
2. Semsarian C, Ingles J, Maron M S, et al. New perspectives on the prevalence of hypertrophic cardiomyopathy. J Am Coll Cardiol, 2015, 65(12): 1249-1254.
3. Corrado D, Pelliccia A, Heidbuchel H, et al. Recommendations for interpretation of 12-lead electrocardiogram in the athlete. Eur Heart J, 2010, 31(2): 243-259.
4. Uberoi A, Stein R, Perez M V, et al. Interpretation of the electrocardiogram of young athletes. Circulation, 2011, 124(6): 746-757.
5. Drezner J A, Ackerman M J, Anderson J, et al. Electrocardiographic interpretation in athletes: The ‘Seattle criteria’. Br J Sports Med, 2013, 47(3): 122-124.
6. Maron B J, Haas T S, Murphy C J, et al. Incidence and causes of sudden death in us college athletes. J Am Coll Cardiol, 2014, 63(16): 1636-1643.
7. 丁士骜, 梅举, 丁芳宝, 等. 肥厚梗阻型心肌病合并重度二尖瓣反流的外科治疗策略. 中国胸心血管外科临床杂志, 2016, 23(7): 675-678.
8. 张妙贤. 超声心动图诊断肥厚型心肌病(HCM)的价值. 中国疗养医学, 2017(11): 60-61.
9. Ripley D P, Musa T A, Dobson L E, et al. Cardiovascular magnetic resonance imaging: What the general cardiologist should know. Heart, 2016, 102(19): 1589-1603.
10. Dominguez F, Gonzalez-Lopez E, Padron-Barthe L, et al. Role of echocardiography in the diagnosis and management of hypertrophic cardiomyopathy. Heart, 2018, 104(3): 260-272.
11. Inciardi R M, Galderisi M, Nistri S, et al. Echocardiographic advances in hypertrophic cardiomyopathy: Three-dimensional and strain imaging echocardiography. Echocardiography, 2018, 35(5): 716-726.
12. Losi M A, Imbriaco M, Canciello G, et al. Left ventricular mass in hypertrophic cardiomyopathy assessed by 2d-echocardiography: Validation with magnetic resonance imaging. J Cardiovasc Transl Res, 2020, 13(2): 238-244.
13. McLeod C J, Ackerman M J, Nishimura R A, et al. Outcome of patients with hypertrophic cardiomyopathy and a normal electrocardiogram. J Am Coll Cardiol, 2009, 54(3): 229-233.
14. Fujii J, Saihara S, Sawada H, et al. Distribution of left ventricular hypertrophy and electrocardiographic findings in patient with so-called apical hypertrophic cardiomyopathy. J Cardiogr Suppl, 1985, 6(6): 23-33.
15. Parisi R, Mirabella F, Secco G G, et al. Multimodality imaging in apical hypertrophic cardiomyopathy. World J Cardiol, 2014, 6(9): 916-923.
16. Ouyang N, Yamauchi K. Using a neural network to diagnose the hypertrophic portions of hypertrophic cardiomyopathy. MD Computing, 1998, 15(2): 106-109.
17. Rahman Q A, Tereshchenko L G, Kongkatong M, et al. Utilizing ECG-based heartbeat classification for hypertrophic cardiomyopathy identification. IEEE Trans Nanobioscience, 2015, 14(5): 505-512.
18. Campbell M J, Zhou X, Han C, et al. Pilot study analyzing automated ECG screening of hypertrophic cardiomyopathy. Heart Rhythm, 2017, 14(6): 848-852.
19. Lyon A, Ariga R, Minchole A, et al. Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers. Front Physiol, 2018, 9: 213.
20. 马志玲, 邵虹, 胡海霞, 等. 肥厚型心肌病体表心电图特征. 心脏杂志, 2018, 30(5): 532-537.
21. Acharya U R, Fujita H, Lih O S, et al. Automated detection of arrhythmias using different intervals of tachycardia ECG segments with convolutional neural network. Inform Sciences, 2017, 405(1): 81-90.
22. Lai D K, Bu Y X, Su Y, et al. Non-standardized patch-based ECG lead together with deep learning based algorithm for automatic screening of atrial fibrillation. IEEE J Biomed Health Inform, 2020, 24(6): 1569-1578.
23. Hannun A Y, Rajpurkar P, Haghpanahi M, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat Med, 2019, 25(1): 65-69.
24. Lai D K, Bu Y X, Su Y, et al. A flexible multilayered dry electrode and assembly to single-lead ECG patch to monitor atrial fibrillation in a real-life scenario. IEEE Sens J, 2020, 20(20): 12295-12306.
25. Bu Y X, Hassan M F U, Lai D K. The embedding of flexible conductive silver-coated electrodes into ECG monitoring garment for minimizing motion artefacts. IEEE Sens J, 2021, 21(13): 14454-14465.
26. 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.
27. Bousseljot R, Kreiseler D, Schnabel A. Nutzung der EKG-Signaldatenbank CARDIODAT der PTB über das Internet. Biomedizinische Technik, 1995, 40(S1): 317-318.
28. Sola J, Sevilla J. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE T Nucl Sci, 1997, 44(3): 1464-1468.
29. Rowin E J, Maron B J, Appelbaum E, et al. Significance of false negative electrocardiograms in preparticipation screening of athletes for hypertrophic cardiomyopathy. Am J Cardiol, 2012, 110(7): 1027-1032.

Journal of Biomedical Engineering

Automatic detection model of hypertrophic cardiomyopathy based on deep convolutional neural network

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content