Lightweight end-to-end model-based korotkoff sounds phase identification and blood pressure measurement_Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Authors：

JIANG Zhiyu ¹ , KOU Wenyi ¹ , LI Li ² , ZHAO Qijun ³ ,  QIAN Yongjun ⁴ ,  PAN Fan ¹

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

Corresponding?author：

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

Keywords：

Korotkoff sounds; phase identification; blood pressure measurement; end-to-end model; deep learning; artificial intelligence; convolutional neural network; gated recurrent unit

DOI：

10.7507/1007-4848.202507061

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Objective To propose a lightweight end-to-end neural network model for automated Korotkoff sound phase recognition and subsequent blood pressure (BP) measurement, aiming to improve measurement accuracy and population adaptability. Methods We developed a streamlined architecture integrating depthwise separable convolution (DSConv), multi-head attention (MHA), and bidirectional gated recurrent unit (BiGRU). The model directly processes Korotkoff sound time-series signals to identify auscultatory phases. Systolic BP (SBP) and diastolic BP (DBP) were determined using phase Ⅰ and phaseⅤdetections, respectively. Given the clinical relevance of phase Ⅳ for specific populations (e.g., children and pregnant women, denoted as DBP_Ⅳ), BP values from this phase were also recorded.Results The study enrolled 106 volunteers with 70 males and 36 females at mean age of (40.0±12.0) years. The model achieved 94.25% phase recognition accuracy. Measurement errors were (0.1±2.5) mm Hg (SBP), (0.9±3.4) mm Hg (DBP_Ⅳ), and (0.8±2.6) mm Hg (DBP). Conclusion Our method enables precise phase recognition and BP measurement, demonstrating potential for developing population-adaptive blood pressure monitoring systems.

Citation： JIANG Zhiyu, KOU Wenyi, LI Li, ZHAO Qijun, QIAN Yongjun, PAN Fan. Lightweight end-to-end model-based korotkoff sounds phase identification and blood pressure measurement. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery, 2026, 33(2): 248-254. doi: 10.7507/1007-4848.202507061 Copy

1.	Babbs CF. The origin of Korotkoff sounds and the accuracy of auscultatory blood pressure measurements. J Am Soc Hypertens, 2015, 9(12): 935-950.
2.	Geddes LA, Hoff HE, Badger AS. Introduction of the auscultatory method of measuring blood pressure—including a translation of Korotkoff's original paper. Cardiovasc Res Cent Bull, 1966, 5(2): 57-74.
3.	Beevers G, Lip GYH, 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.
4.	王文, 張維忠, 孫寧玲, 等. 中國血壓測量指南, 2011, 19(12): 1101-1115.Wang W, Zhang WZ, Sun NL, et al. China blood pressure measurement guidelines. Chin J Hypertens, 2011, 19(12): 1101-1115.
5.	Beardmore Gray A, Dyer R, Shennan A. Blood pressure measurement in pregnancy. Int J Obstet Anesth, 2019, 37: 137-138.
6.	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.
7.	Higgins JR, de Swiet M. Blood-pressure measurement and classification in pregnancy. Lancet, 2001, 357(9250): 131-135.
8.	Meng Z, Zhu 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.
9.	Agnihotram KC, Kumar PW, Muntner P, et al. International consensus on standardized clinic blood pressure measurement - a call to action. Am J Med, 2023, 136(5): 438-445. e1.
10.	段以卓, 鄒玉寶. 臨床上無創血壓測量的方法及應用. 中國分子心臟病學雜志, 2024, 24(1): 5928-5932.Duan YZ, Zou YB. Methods and application of clinical non-invasive blood pressure measurement. Mol Cardiol Chin, 2024, 24(1): 5928-5932.
11.	胡欣宇, 王昕波, 趙召龍, 等. 基于柯氏音法與示波法結合的新型血壓測量系統. 軟件, 2017, 38(3): 78-81.Hu XY, Wang XB, Zhao ZL, et al. A new blood pressure measurement system based on oscillographic and Korotkoff-sound method. Comput Eng Softw, 2017, 38(3): 78-81.
12.	Zhang MY, Cui X, Zhao LW, et al. A lightweight deep learning based bowel sounds segmentation algorithm for gastrointestinal (GI) monitoring. Eng Appl Artif Intell, 2024, 127: 101684.
13.	Xiao D, Zhu F, Jiang J, et al. Leveraging natural cognitive systems in conjunction with ResNet50-BiGRU model and attention mechanism for enhanced medical image analysis and sports injury prediction. Front Neurosci, 2023, 17: 1292858.
14.	Fatima T, Yang WB, Xia KW, et al. Deep learning approach combining GAN and BiGRU for diabetes prediction. In: Proceedings of the 3rd International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC); 2024 Jul 5-7; Mianyang, China. New York: IEEE; 2024.
15.	Hossain S, Chakrabarty A, Gadekallu TR, et al. Vision transformers, ensemble model, and transfer learning leveraging explainable AI for brain tumor detection and classification. IEEE J Biomed Health Inform, 2024, 28(3): 1261-1272.
16.	Ding Y, Zhang S, Tang CG, et al. MASA-TCN: multi-anchor space-aware temporal convolutional neural networks for continuous and discrete EEG emotion recognition. IEEE J Biomed Health Inform, 2024, 28(7): 3953-3964.
17.	Fan P, He P, He W, et al. Development and validation of a deep learning-based automatic auscultatory blood pressure measurement method. Biomed Signal Process Control, 2021, 68: 102713.
18.	Pan F, He PY, Chen F, et al. A novel deep learning based automatic auscultatory method to measure blood pressure. Int J Med Inform, 2019, 128: 71-78.
19.	Argha A, Celler BG, Lovell NH. A novel automated blood pressure estimation algorithm using sequences of Korotkoff sounds. IEEE J Biomed Health Inform, 2020, 24(10): 2744-2754.
20.	Argha A, Celler BG, Alinejad-Rokny H, et al. Blood pressure estimation from Korotkoff sound signals using an end-to-end deep-learning-based algorithm. IEEE Trans Instrum Meas, 2022, 71: 4002610.
21.	陳俊輝, 何培宇, 方安成, 等. 基于深度學習的柯氏音時相分類研究. 中國胸心血管外科臨床雜志, 2023, 30(1): 25-31.Chen JH, He PY, Fang AC, et al. Research on classification of Korotkoff sound phases based on deep learning. Chin J Clin Thorac Cardiovasc Surg, 2023, 30(1): 25-31.
22.	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.
23.	Pan F, Chen F, Liu C, et al. Quantitative comparison of Korotkoff sound waveform characteristics: effects of static cuff pressures and stethoscope positions. Ann Biomed Eng, 2018, 46(11): 1736-1744.
24.	Chollet F. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 Jul 21-26; Honolulu, HI. New York: IEEE; 2017: 1800-1807.
25.	Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017 Dec 4-9; Long Beach, CA. Red Hook: Curran Associates Inc. 2017: 5998-6008.
26.	Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. Preprint. Posted online December 11, 2014. arXiv: 1412.3555.

1. Babbs CF. The origin of Korotkoff sounds and the accuracy of auscultatory blood pressure measurements. J Am Soc Hypertens, 2015, 9(12): 935-950.
2. Geddes LA, Hoff HE, Badger AS. Introduction of the auscultatory method of measuring blood pressure—including a translation of Korotkoff's original paper. Cardiovasc Res Cent Bull, 1966, 5(2): 57-74.
3. Beevers G, Lip GYH, 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.
4. 王文, 張維忠, 孫寧玲, 等. 中國血壓測量指南, 2011, 19(12): 1101-1115.Wang W, Zhang WZ, Sun NL, et al. China blood pressure measurement guidelines. Chin J Hypertens, 2011, 19(12): 1101-1115.
5. Beardmore Gray A, Dyer R, Shennan A. Blood pressure measurement in pregnancy. Int J Obstet Anesth, 2019, 37: 137-138.
6. 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.
7. Higgins JR, de Swiet M. Blood-pressure measurement and classification in pregnancy. Lancet, 2001, 357(9250): 131-135.
8. Meng Z, Zhu 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.
9. Agnihotram KC, Kumar PW, Muntner P, et al. International consensus on standardized clinic blood pressure measurement - a call to action. Am J Med, 2023, 136(5): 438-445. e1.
10. 段以卓, 鄒玉寶. 臨床上無創血壓測量的方法及應用. 中國分子心臟病學雜志, 2024, 24(1): 5928-5932.Duan YZ, Zou YB. Methods and application of clinical non-invasive blood pressure measurement. Mol Cardiol Chin, 2024, 24(1): 5928-5932.
11. 胡欣宇, 王昕波, 趙召龍, 等. 基于柯氏音法與示波法結合的新型血壓測量系統. 軟件, 2017, 38(3): 78-81.Hu XY, Wang XB, Zhao ZL, et al. A new blood pressure measurement system based on oscillographic and Korotkoff-sound method. Comput Eng Softw, 2017, 38(3): 78-81.
12. Zhang MY, Cui X, Zhao LW, et al. A lightweight deep learning based bowel sounds segmentation algorithm for gastrointestinal (GI) monitoring. Eng Appl Artif Intell, 2024, 127: 101684.
13. Xiao D, Zhu F, Jiang J, et al. Leveraging natural cognitive systems in conjunction with ResNet50-BiGRU model and attention mechanism for enhanced medical image analysis and sports injury prediction. Front Neurosci, 2023, 17: 1292858.
14. Fatima T, Yang WB, Xia KW, et al. Deep learning approach combining GAN and BiGRU for diabetes prediction. In: Proceedings of the 3rd International Conference on Robotics, Artificial Intelligence and Intelligent Control (RAIIC); 2024 Jul 5-7; Mianyang, China. New York: IEEE; 2024.
15. Hossain S, Chakrabarty A, Gadekallu TR, et al. Vision transformers, ensemble model, and transfer learning leveraging explainable AI for brain tumor detection and classification. IEEE J Biomed Health Inform, 2024, 28(3): 1261-1272.
16. Ding Y, Zhang S, Tang CG, et al. MASA-TCN: multi-anchor space-aware temporal convolutional neural networks for continuous and discrete EEG emotion recognition. IEEE J Biomed Health Inform, 2024, 28(7): 3953-3964.
17. Fan P, He P, He W, et al. Development and validation of a deep learning-based automatic auscultatory blood pressure measurement method. Biomed Signal Process Control, 2021, 68: 102713.
18. Pan F, He PY, Chen F, et al. A novel deep learning based automatic auscultatory method to measure blood pressure. Int J Med Inform, 2019, 128: 71-78.
19. Argha A, Celler BG, Lovell NH. A novel automated blood pressure estimation algorithm using sequences of Korotkoff sounds. IEEE J Biomed Health Inform, 2020, 24(10): 2744-2754.
20. Argha A, Celler BG, Alinejad-Rokny H, et al. Blood pressure estimation from Korotkoff sound signals using an end-to-end deep-learning-based algorithm. IEEE Trans Instrum Meas, 2022, 71: 4002610.
21. 陳俊輝, 何培宇, 方安成, 等. 基于深度學習的柯氏音時相分類研究. 中國胸心血管外科臨床雜志, 2023, 30(1): 25-31.Chen JH, He PY, Fang AC, et al. Research on classification of Korotkoff sound phases based on deep learning. Chin J Clin Thorac Cardiovasc Surg, 2023, 30(1): 25-31.
22. 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.
23. Pan F, Chen F, Liu C, et al. Quantitative comparison of Korotkoff sound waveform characteristics: effects of static cuff pressures and stethoscope positions. Ann Biomed Eng, 2018, 46(11): 1736-1744.
24. Chollet F. Xception: deep learning with depthwise separable convolutions. In: Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); 2017 Jul 21-26; Honolulu, HI. New York: IEEE; 2017: 1800-1807.
25. Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems; 2017 Dec 4-9; Long Beach, CA. Red Hook: Curran Associates Inc. 2017: 5998-6008.
26. Chung J, Gulcehre C, Cho K, et al. Empirical evaluation of gated recurrent neural networks on sequence modeling. Preprint. Posted online December 11, 2014. arXiv: 1412.3555.

Chinese Journal of Clinical Thoracic and Cardiovascular Surgery

Lightweight end-to-end model-based korotkoff sounds phase identification and blood pressure measurement

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content