Research on classification of Korotkoff sounds phases based on deep learning_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

CHEN Junhui ¹ , HE Peiyu ¹ , FANG Ancheng ¹ , WANG Zhengjie ² , TONG Qi ² , ZHAO Qijun ³ ,  PAN Fan ¹ ,  QIAN Yongjun ²

1. School of Electronic Information, Sichuan University, Chengdu, 610065, P. R. China;
2. Department of Cardiovascular Surgery, West China Hospital, Sichuan University, Chengdu, 610041, P. R. China;
3. School of Computer Science, Sichuan University, Chengdu, 610065, P. R. China;

Corresponding?author：

PAN Fan, Email: panfan@scu.edu.cn; QIAN Yongjun, Email: qianyongjun@scu.edu.cn

Keywords：

Classification of Korotkoff sounds phases; blood pressure measurement; attention mechanism; residual network; bidirectional long short-term memory

DOI：

10.7507/1007-4848.202207007

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To recognize the different phases of Korotkoff sounds through deep learning technology, so as to improve the accuracy of blood pressure measurement in different populations. Methods A classification model of the Korotkoff sounds phases was designed, which fused attention mechanism (Attention), residual network (ResNet) and bidirectional long short-term memory (BiLSTM). First, a single Korotkoff sound signal was extracted from the whole Korotkoff sounds signals beat by beat, and each Korotkoff sound signal was converted into a Mel spectrogram. Then, the local feature extraction of Mel spectrogram was processed by using the Attention mechanism and ResNet network, and BiLSTM network was used to deal with the temporal relations between features, and full-connection layer network was applied in reducing the dimension of features. Finally, the classification was completed by SoftMax function. The dataset used in this study was collected from 44 volunteers (24 females, 20 males with an average age of 36 years), and the model performance was verified using 10-fold cross-validation. Results The classification accuracy of the established model for the 5 types of Korotkoff sounds phases was 93.4%, which was higher than that of other models. Conclusion This study proves that the deep learning method can accurately classify Korotkoff sounds phases, which lays a strong technical foundation for the subsequent design of automatic blood pressure measurement methods based on the classification of the Korotkoff sounds phases.

Citation： CHEN Junhui, HE Peiyu, FANG Ancheng, WANG Zhengjie, TONG Qi, ZHAO Qijun, PAN Fan, QIAN Yongjun. Research on classification of Korotkoff sounds phases based on deep learning. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2023, 30(1): 25-31. doi: 10.7507/1007-4848.202207007 Copy

1.	Beevers G, Lip GY, O'Brien E. ABC of hypertension: Blood pressure measurement. Part Ⅱ-conventional sphygmomanometry: Technique of auscultatory blood pressure measurement. BMJ, 2001, 322(7293): 1043-1047.
2.	代小莉, 李作君. 特殊人群的血壓測量. 世界最新醫學信息文摘, 2015, 15(37): 98.
3.	Babbs CF. The origin of Korotkoff sounds and the accuracy of auscultatory blood pressure measurements. J Am Soc Hypertens, 2015, 9(12): 935-950.
4.	《中國高血壓基層管理指南》修訂委員會. 中國高血壓基層管理指南(2014年修訂版). 中華高血壓雜志, 2015, 23(1): 24-43.
5.	Venet R, Miric D, Pavie A, et al. Korotkoff sound: The cavitation hypothesis. Med Hypotheses, 2000, 55(2): 141-146.
6.	王文, 張繼忠, 孫寧玲, 等. 中國血壓測量指南. 中華血壓雜志, 2011, 19(12): 1101-1115.
7.	Celler BG, Butlin M, Argha A, et al. Are Korotkoff sounds reliable markers for accurate estimation of systolic and diastolic pressure using brachial cuff sphygmomanometry? IEEE Trans Biomed Eng, 2021, 68(12): 3593-3601.
8.	Brown MA, Reiter L, Smith B, et al. Measuring blood pressure in pregnant women: A comparison of direct and indirect methods. Am J Obstet Gynecol, 1994, 171(3): 661-667.
9.	Zhang M, Zhang X, Chen F, et al. Effects of room environment and nursing experience on clinical blood pressure measurement: An observational study. Blood Press Monit, 2017, 22(2): 79-85.
10.	Pickering TG, Hall JE, Appel LJ, et al. Recommendations for blood pressure measurement in humans and experimental animals: Part 1: Blood pressure measurement in humans: A statement for professionals from the Subcommittee of Professional and Public Education of the American Heart Association Council on High Blood Pressure Research. Circulation, 2005, 111(5): 697-716.
11.	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. CVPR, 2016: 770-778.
12.	Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735-1780.
13.	Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, 542(7639): 115-118.
14.	Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016, 316(22): 2402-2410.
15.	王永軍, 黃芳琳, 黃珊, 等. 基于融合多網絡深層卷積特征和稀疏雙關系正則化方法的乳腺癌圖像分類研究. 中國生物醫學工程學報, 2020, 39(5): 532-540.
16.	汪佳衡, 王躍明, 姚林. 基于濾波器組長短時記憶網絡的腦電信號情緒識別. 生物醫學工程學雜志, 2021, 38(3): 447-454.
17.	Shivam A, Kiran K, Devanjali R. Security threat sounds classification using Neural Network. INDIACom, 2021: 690-694.
18.	Tohru K, Naoki A et al. Automatic classification of respiratory sounds considering time series information based on VGG16 with LSTM. ICCAS, 2020: 423-426.
19.	李偉, 楊向東, 陳懇. 基于CNN和RNN聯合網絡的心音自動分類. 計算機工程與設計, 2020, 41(1): 46-51.
20.	Deng L, Hinton G, Kingsbury B. New types of deep neural network learning for speech recognition and related applications: An overview. ICASSP, 2013: 8599-8603.
21.	Pan F, He P, Liu C, et al. Variation of the Korotkoff stethoscope sounds during blood pressure measurement: Analysis using a convolutional neural network. IEEE J Biomed Health Inform, 2017, 21(6): 1593-1598.
22.	Park DK, Kang JH, Kim IY, et al. Novel method of automatic auscultation for blood pressure measurement using pulses in cuff pressure and korotkoff sound. CIC, 2008: 181-184.
23.	Pan F, He PY, Wang H, et al. Development and validation of a deep learning-based automatic auscultatory blood pressure measurement method. Biomed Signal Process Control, 2021, 68: 102742.
24.	Dziban N, Agung WS, Tati LER. Blood pressure measuring device based on Korotkoff sound’s tapping period and frequency detection. ISITIA, 2020: 158-163.
25.	Allen J, Gehrke T, O'Sullivan JJ, et al. Characterization of the Korotkoff sounds using joint time-frequency analysis. Physiol Meas, 2004, 25(1): 107-117.

1. Beevers G, Lip GY, O'Brien E. ABC of hypertension: Blood pressure measurement. Part Ⅱ-conventional sphygmomanometry: Technique of auscultatory blood pressure measurement. BMJ, 2001, 322(7293): 1043-1047.
2. 代小莉, 李作君. 特殊人群的血壓測量. 世界最新醫學信息文摘, 2015, 15(37): 98.
3. Babbs CF. The origin of Korotkoff sounds and the accuracy of auscultatory blood pressure measurements. J Am Soc Hypertens, 2015, 9(12): 935-950.
4. 《中國高血壓基層管理指南》修訂委員會. 中國高血壓基層管理指南(2014年修訂版). 中華高血壓雜志, 2015, 23(1): 24-43.
5. Venet R, Miric D, Pavie A, et al. Korotkoff sound: The cavitation hypothesis. Med Hypotheses, 2000, 55(2): 141-146.
6. 王文, 張繼忠, 孫寧玲, 等. 中國血壓測量指南. 中華血壓雜志, 2011, 19(12): 1101-1115.
7. Celler BG, Butlin M, Argha A, et al. Are Korotkoff sounds reliable markers for accurate estimation of systolic and diastolic pressure using brachial cuff sphygmomanometry? IEEE Trans Biomed Eng, 2021, 68(12): 3593-3601.
8. Brown MA, Reiter L, Smith B, et al. Measuring blood pressure in pregnant women: A comparison of direct and indirect methods. Am J Obstet Gynecol, 1994, 171(3): 661-667.
9. Zhang M, Zhang X, Chen F, et al. Effects of room environment and nursing experience on clinical blood pressure measurement: An observational study. Blood Press Monit, 2017, 22(2): 79-85.
10. Pickering TG, Hall JE, Appel LJ, et al. Recommendations for blood pressure measurement in humans and experimental animals: Part 1: Blood pressure measurement in humans: A statement for professionals from the Subcommittee of Professional and Public Education of the American Heart Association Council on High Blood Pressure Research. Circulation, 2005, 111(5): 697-716.
11. He K, Zhang X, Ren S, et al. Deep residual learning for image recognition. CVPR, 2016: 770-778.
12. Hochreiter S, Schmidhuber J. Long short-term memory. Neural Comput, 1997, 9(8): 1735-1780.
13. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature, 2017, 542(7639): 115-118.
14. Gulshan V, Peng L, Coram M, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA, 2016, 316(22): 2402-2410.
15. 王永軍, 黃芳琳, 黃珊, 等. 基于融合多網絡深層卷積特征和稀疏雙關系正則化方法的乳腺癌圖像分類研究. 中國生物醫學工程學報, 2020, 39(5): 532-540.
16. 汪佳衡, 王躍明, 姚林. 基于濾波器組長短時記憶網絡的腦電信號情緒識別. 生物醫學工程學雜志, 2021, 38(3): 447-454.
17. Shivam A, Kiran K, Devanjali R. Security threat sounds classification using Neural Network. INDIACom, 2021: 690-694.
18. Tohru K, Naoki A et al. Automatic classification of respiratory sounds considering time series information based on VGG16 with LSTM. ICCAS, 2020: 423-426.
19. 李偉, 楊向東, 陳懇. 基于CNN和RNN聯合網絡的心音自動分類. 計算機工程與設計, 2020, 41(1): 46-51.
20. Deng L, Hinton G, Kingsbury B. New types of deep neural network learning for speech recognition and related applications: An overview. ICASSP, 2013: 8599-8603.
21. Pan F, He P, Liu C, et al. Variation of the Korotkoff stethoscope sounds during blood pressure measurement: Analysis using a convolutional neural network. IEEE J Biomed Health Inform, 2017, 21(6): 1593-1598.
22. Park DK, Kang JH, Kim IY, et al. Novel method of automatic auscultation for blood pressure measurement using pulses in cuff pressure and korotkoff sound. CIC, 2008: 181-184.
23. Pan F, He PY, Wang H, et al. Development and validation of a deep learning-based automatic auscultatory blood pressure measurement method. Biomed Signal Process Control, 2021, 68: 102742.
24. Dziban N, Agung WS, Tati LER. Blood pressure measuring device based on Korotkoff sound’s tapping period and frequency detection. ISITIA, 2020: 158-163.
25. Allen J, Gehrke T, O'Sullivan JJ, et al. Characterization of the Korotkoff sounds using joint time-frequency analysis. Physiol Meas, 2004, 25(1): 107-117.

Previous Article
A new classification of congenital biliary dilatation—HUAXI CBD classification
Next Article
提高人文修養是成為杏林翹楚的前提

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Research on classification of Korotkoff sounds phases based on deep learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content