Heart sound model based on DenseNet121 architecture for diagnosis of aortic stenosis: A prospective clinical trial_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

CHEN Zhengda ^1,2 , FU Bo ¹ , WANG Jianyu ^1,2 , JIANG Nan ¹ ,  GUO Zhigang ¹

1. Department of Cardiovascular Surgery, Tianjin Chest Hospital, Tianjin, 300222, P. R. China;
2. Tianjin Medical University, Tianjin, 300070, P. R. China;

Corresponding author：

GUO Zhigang, Email: hanyong_td@163.com

Keywords：

Aortic stenosis; deep learning; heart sounds; artificial intelligence

DOI：

10.7507/1007-4848.202209056

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To identify the heart sounds of aortic stenosis by deep learning model based on DenseNet121 architecture, and to explore its application potential in clinical screening aortic stenosis. Methods We prospectively collected heart sounds and clinical data of patients with aortic stenosis in Tianjin Chest Hospital, from June 2021 to February 2022. The collected heart sound data were used to train, verify and test a deep learning model. We evaluated the performance of the model by drawing receiver operating characteristic curve and precision-recall curve. Results A total of 100 patients including 11 asymptomatic patients were included. There were 50 aortic stenosis patients with 30 males and 20 females at an average age of 68.18±10.63 years in an aortic stenosis group (stenosis group). And 50 patients without aortic valve disease were in a negative group, including 26 males and 24 females at an average age of 45.98±12.51 years. The model had an excellent ability to distinguish heart sound data collected from patients with aortic stenosis in clinical settings: accuracy at 91.67%, sensitivity at 90.00%, specificity at 92.50%, and area under receiver operating characteristic curve was 0.917. Conclusion The model of heart sound diagnosis of aortic stenosis based on deep learning has excellent application prospects in clinical screening, which can provide a new idea for the early identification of patients with aortic stenosis.

Citation： CHEN Zhengda, FU Bo, WANG Jianyu, JIANG Nan, GUO Zhigang. Heart sound model based on DenseNet121 architecture for diagnosis of aortic stenosis: A prospective clinical trial. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2023, 30(4): 514-521. doi: 10.7507/1007-4848.202209056 Copy

1.	Turina J, Hess OM, Krayenbuhl HP. Spontaneous course of aortic valve disease and indications for aortic valve replacement. Schweiz Med Wochenschr, 1988, 118(14): 508-516.
2.	Kelly TA, Rothbart RM, Cooper CM, et al. Comparison of outcome of asymptomatic to symptomatic patients older than 20 years of age with valvular aortic stenosis. Am J Cardiol, 1988, 61(1): 123-130.
3.	Eveborn GW, Schirmer H, Heggelund G, et al. The evolving epidemiology of valvular aortic stenosis. The Tromso study. Heart, 2013, 99(6): 396-400.
4.	Baumgartner H, Hung J, Bermejo J, et al. Recommendations on the echocardiographic assessment of aortic valve stenosis: A focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography. Eur Heart J Cardiovasc Imaging, 2017, 18(3): 254-275.
5.	Iung B, Vahanian A. Epidemiology of valvular heart disease in the adult. Nat Rev Cardiol, 2011, 8(3): 162-172.
6.	Jan MF, Tajik AJ. Auscultatory interregnum: Bicentennial of the Stethoscope. Circulation, 2020, 142(8): 715-716.
7.	David SG, Angelo T, Mario S, et al. Computer analysis of phonocardiograms. Prog Cardiovas Dis, 1963, 5(4): 393-405.
8.	Li S, Li F, Tang S, et al. A review of computer-aided heart sound detection techniques. Biomed Res Int, 2020: 20205846191.
9.	Liu C, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
10.	Clifford GD, Liu C, Moody B, et al. Classification of normal/abnormal heart sound recordings: The physionet/computing in cardiology challenge 2016. Computing in Cardiology. IEEE, 2017.
11.	Huang G, Liu Z, Van-Der-Maaten L, et al. Densely connected convolutional networks. 2017: 2261-2269.
12.	Sztajzel JM, Picard-Kossovsky M, Lerch R, et al. Accuracy of cardiac auscultation in the era of Doppler-echocardiography: A comparison between cardiologists and internists. Int J Cardiol, 2010, 138(3): 308-310.
13.	Dwivedi AK, Imtiaz SA, Rodriguez-Villegas E. Algorithms for automatic analysis and classification of heart sounds–A systematic review. IEEE Access, 2019, 78316-8345.
14.	Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, et al. Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors. IEEE Trans Biomed Circuits Syst, 2018, 12(1): 24-34.
15.	Siddique L, Muhammad U, Rajib R, et al. Phonocardiographic sensing using deep learning for abnormal heartbeat detection. IEEE Sensors J, 2018, 18(22): 9393-9400.
16.	Sotaquira M, Alvear D, Mondragon M. Phonocardiogram classification using deep neural networks and weighted probability comparisons. J Med Eng Technol, 2018, 42(7): 510-517.
17.	Yaseen, Son GY, Soonil K. Classification of heart sound signal using multiple features. Appl Sci, 2018, 8(12): 2344.
18.	Oh SL, Jahmunah V, Ooi CP, et al. Classification of heart sound signals using a novel deep WaveNet model. Comput Methods Programs Biomed, 2020: 196105604.
19.	Baghel N, Dutta M-K, Burget R. Automatic diagnosis of multiple cardiac diseases from PCG signals using convolutional neural network. Comput Methods Programs Biomed, 2020, 197: 105750.
20.	Li Z, Chang Y, Schuller BW. CNN-based heart sound classification with an imbalance-compensating weighted loss function. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 4934-4937.
21.	Cho J, Lee K, Shin E, et al. How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? The International Conference on Learning Representations, 2016.
22.	Qiu W, Qian K, Wang Z, et al. A federated learning paradigm for heart sound classification. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 1045-1048.
23.	Hyunkwang L, Shahein T, Jenny L, et al. Fully automated deep learning system for bone age assessment. J Dig Image, 2017, 30(4): 427-441.
24.	Strodthoff N, Strodthoff C. Detecting and interpreting myocardial infarction using fully convolutional neural networks. Physiol Measure, 2019, 40(1): 15001.
25.	Liu J, Wang HL, Yang Z, et al. Deep learning-based computer-aided heart sound analysis in children with left-to-right shunt congenital heart disease. Int J Cardiol, 2022, 348: 58-64.

1. Turina J, Hess OM, Krayenbuhl HP. Spontaneous course of aortic valve disease and indications for aortic valve replacement. Schweiz Med Wochenschr, 1988, 118(14): 508-516.
2. Kelly TA, Rothbart RM, Cooper CM, et al. Comparison of outcome of asymptomatic to symptomatic patients older than 20 years of age with valvular aortic stenosis. Am J Cardiol, 1988, 61(1): 123-130.
3. Eveborn GW, Schirmer H, Heggelund G, et al. The evolving epidemiology of valvular aortic stenosis. The Tromso study. Heart, 2013, 99(6): 396-400.
4. Baumgartner H, Hung J, Bermejo J, et al. Recommendations on the echocardiographic assessment of aortic valve stenosis: A focused update from the European Association of Cardiovascular Imaging and the American Society of Echocardiography. Eur Heart J Cardiovasc Imaging, 2017, 18(3): 254-275.
5. Iung B, Vahanian A. Epidemiology of valvular heart disease in the adult. Nat Rev Cardiol, 2011, 8(3): 162-172.
6. Jan MF, Tajik AJ. Auscultatory interregnum: Bicentennial of the Stethoscope. Circulation, 2020, 142(8): 715-716.
7. David SG, Angelo T, Mario S, et al. Computer analysis of phonocardiograms. Prog Cardiovas Dis, 1963, 5(4): 393-405.
8. Li S, Li F, Tang S, et al. A review of computer-aided heart sound detection techniques. Biomed Res Int, 2020: 20205846191.
9. Liu C, Springer D, Li Q, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas, 2016, 37(12): 2181-2213.
10. Clifford GD, Liu C, Moody B, et al. Classification of normal/abnormal heart sound recordings: The physionet/computing in cardiology challenge 2016. Computing in Cardiology. IEEE, 2017.
11. Huang G, Liu Z, Van-Der-Maaten L, et al. Densely connected convolutional networks. 2017: 2261-2269.
12. Sztajzel JM, Picard-Kossovsky M, Lerch R, et al. Accuracy of cardiac auscultation in the era of Doppler-echocardiography: A comparison between cardiologists and internists. Int J Cardiol, 2010, 138(3): 308-310.
13. Dwivedi AK, Imtiaz SA, Rodriguez-Villegas E. Algorithms for automatic analysis and classification of heart sounds–A systematic review. IEEE Access, 2019, 78316-8345.
14. Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, et al. Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors. IEEE Trans Biomed Circuits Syst, 2018, 12(1): 24-34.
15. Siddique L, Muhammad U, Rajib R, et al. Phonocardiographic sensing using deep learning for abnormal heartbeat detection. IEEE Sensors J, 2018, 18(22): 9393-9400.
16. Sotaquira M, Alvear D, Mondragon M. Phonocardiogram classification using deep neural networks and weighted probability comparisons. J Med Eng Technol, 2018, 42(7): 510-517.
17. Yaseen, Son GY, Soonil K. Classification of heart sound signal using multiple features. Appl Sci, 2018, 8(12): 2344.
18. Oh SL, Jahmunah V, Ooi CP, et al. Classification of heart sound signals using a novel deep WaveNet model. Comput Methods Programs Biomed, 2020: 196105604.
19. Baghel N, Dutta M-K, Burget R. Automatic diagnosis of multiple cardiac diseases from PCG signals using convolutional neural network. Comput Methods Programs Biomed, 2020, 197: 105750.
20. Li Z, Chang Y, Schuller BW. CNN-based heart sound classification with an imbalance-compensating weighted loss function. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 4934-4937.
21. Cho J, Lee K, Shin E, et al. How much data is needed to train a medical image deep learning system to achieve necessary high accuracy? The International Conference on Learning Representations, 2016.
22. Qiu W, Qian K, Wang Z, et al. A federated learning paradigm for heart sound classification. Annu Int Conf IEEE Eng Med Biol Soc, 2022, 2022: 1045-1048.
23. Hyunkwang L, Shahein T, Jenny L, et al. Fully automated deep learning system for bone age assessment. J Dig Image, 2017, 30(4): 427-441.
24. Strodthoff N, Strodthoff C. Detecting and interpreting myocardial infarction using fully convolutional neural networks. Physiol Measure, 2019, 40(1): 15001.
25. Liu J, Wang HL, Yang Z, et al. Deep learning-based computer-aided heart sound analysis in children with left-to-right shunt congenital heart disease. Int J Cardiol, 2022, 348: 58-64.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Heart sound model based on DenseNet121 architecture for diagnosis of aortic stenosis: A prospective clinical trial

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content