Skip to main content

Advertisement

SpringerLink
Log in

Heart function grading evaluation based on heart sounds and convolutional neural networks

  • Scientific Paper
  • Published:
Physical and Engineering Sciences in Medicine Aims and scope Submit manuscript

Abstract

Accurate and rapid cardiac function assessment is critical for disease diagnosis and treatment strategy. However, the current cardiac function assessment methods have their adaptability and limitations. Heart sounds (HS) can reflect changes in heart function. Therefore, HS signals were proposed to assess cardiac function, and a specially designed pruning convolutional neural network (CNN) was applied to recognize subjects’ cardiac function at different levels in this paper. Firstly, the adaptive wavelet denoising algorithm and logistic regression based hidden semi-Markov model were utilized for signal denoising and segmentation. Then, the continuous wavelet transform (CWT) was employed to convert the preprocessed HS signals into spectra as input to the convolutional neural network, which can extract features automatically. Finally, the proposed method was compared with AlexNet, Resnet50, Xception, GhostNet and EfficientNet to verify the superiority of the proposed method. Through comprehensive comparison, the proposed approach achieves the best classification performance with an accuracy of 94.34%. The study indicates HS analysis is a non-invasive and effective method for cardiac function classification, which has broad research prospects.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

Data availability

The database is not publicly available due to the interest of National Natural Science Foundation of China.

Code availability

Information about the code can be reached at xiaoch@cqu.edu.cn.

References

  1. World Health Organization (2017) Cardiovascular diseases. https://www.who.int/health-topics/cardiovascular-diseases. Accessed 24 Jul 2022

  2. Briongos-Figuero S, Estévez A, Pérez ML et al (2020) Prognostic role of NYHA class in heart failure patients undergoing primary prevention ICD therapy. ESC Heart Fail 7:279–283. https://doi.org/10.1002/ehf2.12548

    Article  PubMed  Google Scholar 

  3. Zhang R, Ma S, Shanahan L et al (2018) Discovering and identifying New York heart association classification from electronic health records. BMC Med Inform Decis Mak 18. https://doi.org/10.1186/s12911-018-0625-7

  4. Landolina M, Lunati M, Gasparini M et al (2007) Comparison of the effects of cardiac resynchronization therapy in patients with class II versus class III and IV heart failure (from the InSync/InSync ICD Italian Registry). Am J Cardiol 100:1007–1012. https://doi.org/10.1016/j.amjcard.2007.04.043

    Article  PubMed  Google Scholar 

  5. Trappe HJ, Wenzlaff P, Pfitzner P, Fieguth HG (1997) Long term follow up of patients with implantable cardioverter- defibrillators and mild, moderate, or severe impairment of left ventricular function. Heart 78:243–249. https://doi.org/10.1136/hrt.78.3.243

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  6. Bennett JA, Riegel B, Bittner V, Nichols J (2002) Validity and reliability of the NYHA classes for measuring research outcomes in patients with cardiac disease. Heart and Lung: Journal of Acute and Critical Care 31:262–270. https://doi.org/10.1067/mhl.2002.124554

    Article  PubMed  Google Scholar 

  7. The Criteria Committee of the New York Heart Association (1974) Nomenclature and criteria for diagnosis of diseases of the heart and great blood vessels. Am Heart J 88:679. https://doi.org/10.1016/0002-8703(74)90267-1

    Article  Google Scholar 

  8. Raphael C, Briscoe C, Davies J et al (2007) Limitations of the New York Heart Association functional classification system and self-reported walking distances in chronic heart failure. Heart 93:476–482. https://doi.org/10.1136/hrt.2006.089656

    Article  PubMed  Google Scholar 

  9. Yap J, Lim FY, Gao F et al (2015) Correlation of the New York Heart Association classification and the 6-minute walk distance: a systematic review. Clin Cardiol 38:621–628. https://doi.org/10.1002/clc.22468

    Article  PubMed  PubMed Central  Google Scholar 

  10. Wu C, Herman BA, Retta SM et al (2005) On the closing sounds of a mechanical heart valve. Ann Biomed Eng 33:743–750. https://doi.org/10.1007/s10439-005-3237-1

    Article  PubMed  Google Scholar 

  11. Zheng Y, Guo X, Qin J, Xiao S (2015) Computer-assisted diagnosis for chronic heart failure by the analysis of their cardiac reserve and heart sound characteristics. Comput Methods Programs Biomed 122:372–383. https://doi.org/10.1016/j.cmpb.2015.09.001

    Article  PubMed  Google Scholar 

  12. Leng S, Tan RS, Chai KTC et al (2015) The electronic stethoscope. Biomed Eng Online. https://doi.org/10.1186/s12938-015-0056-y. 14:

    Article  PubMed  PubMed Central  Google Scholar 

  13. Yan H, Wei X, Han F, Lin J (2011) Monitoring the impact of general anesthesia induction and endotracheal intubations on cardiac performance by phonocardiogram. 23:231–236. https://doi.org/10.4015/S1016237211002566

  14. Manecke GR, Nemirov MA, Bicker AA et al (1999) The effect of halothane on the amplitude and frequency characteristics of heart sounds in children. Anesth Analg 88:263–270

    Article  CAS  PubMed  Google Scholar 

  15. Guo X, Ding X, Lei M et al (2012) Non-invasive monitoring and evaluating cardiac function of pregnant women based on a relative value method. Acta Physiol Hung 99:382–391. https://doi.org/10.1556/APhysiol.99.2012.4.2

    Article  PubMed  Google Scholar 

  16. Joshi RC, Khan JS, Pathak VK, Dutta MK (2022) AI-CardioCare: Artificial Intelligence Based device for Cardiac Health Monitoring. IEEE Trans Hum Mach Syst. https://doi.org/10.1109/THMS.2022.3211460

    Article  Google Scholar 

  17. el Badlaoui O, Benba A, Hammouch A (2020) Novel PCG analysis Method for discriminating between abnormal and normal heart sounds. IRBM 41:223–228. https://doi.org/10.1016/j.irbm.2019.12.003

    Article  Google Scholar 

  18. Zhang W, Han J, Deng S (2017) Heart sound classification based on scaled spectrogram and tensor decomposition. Expert Syst Appl 84:220–231. https://doi.org/10.1016/j.eswa.2017.05.014

    Article  Google Scholar 

  19. Wu JMT, Tsai MH, Huang YZ et al (2019) Applying an ensemble convolutional neural network with Savitzky–Golay filter to construct a phonocardiogram prediction model. Appl Soft Comput J 78:29–40. https://doi.org/10.1016/j.asoc.2019.01.019

    Article  Google Scholar 

  20. Levin AD, Ragazzi A, Szot SL, Ning T (2022) Extraction and assessment of diagnosis-relevant features for heart murmur classification. Methods 202:110–116. https://doi.org/10.1016/j.ymeth.2021.07.002

    Article  CAS  PubMed  Google Scholar 

  21. Rath A, Mishra D, Panda G, Pal M (2022) Development and assessment of machine learning based heart disease detection using imbalanced heart sound signal. Biomed Signal Process Control 76. https://doi.org/10.1016/j.bspc.2022.103730

  22. Barua PD, Karasu M, Kobat MA et al (2022) An accurate valvular heart disorders detection model based on a new dual symmetric tree pattern using stethoscope sounds. Comput Biol Med 146:105599. https://doi.org/10.1016/j.compbiomed.2022.105599

    Article  PubMed  Google Scholar 

  23. Mehmet Bilal ER (2021) Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features. Appl Acoust 180. https://doi.org/10.1016/j.apacoust.2021.108152

  24. Bozkurt B, Germanakis I, Stylianou Y (2018) A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection. Comput Biol Med 100:132–143. https://doi.org/10.1016/j.compbiomed.2018.06.026

    Article  PubMed  Google Scholar 

  25. Zang X, Li B, Zhao L et al (2022) End-to-end depression recognition based on a one-dimensional convolution neural network model using two-lead ECG Signal. J Med Biol Eng 42:225–233. https://doi.org/10.1007/s40846-022-00687-7

    Article  PubMed  PubMed Central  Google Scholar 

  26. Satapathy SK, Loganathan D (2022) Automated classification of multi-class sleep stages classification using polysomnography signals: a nine- layer 1D-convolution neural network approach. Multimed Tools Appl. https://doi.org/10.1007/s11042-022-13195-2

    Article  Google Scholar 

  27. Chatterjee S, Thakur RS, Yadav RN, Gupta L (2022) Sparsity-based modified wavelet denoising autoencoder for ECG signals. Signal Processing 198. https://doi.org/10.1016/j.sigpro.2022.108605

  28. Jadhav P, Rajguru G, Datta D, Mukhopadhyay S (2020) Automatic sleep stage classification using time-frequency images of CWT and transfer learning using convolution neural network. Biocybern Biomed Eng 40:494–504. https://doi.org/10.1016/j.bbe.2020.01.010

    Article  Google Scholar 

  29. Giorgio A, Guaragnella C, Rizzi M (2022) An effective CAD system for heart sound abnormality detection. Circuits Syst Signal Process 41:2845–2870. https://doi.org/10.1007/s00034-021-01916-1

    Article  Google Scholar 

  30. Omari T, Bereksi-Reguig F (2015) An automatic wavelet selection scheme for heart sounds denoising. Int J Wavelets Multiresolut Inf Process 13. https://doi.org/10.1142/S0219691315500149

  31. Liu C, Springer D, Li Q et al (2016) An open access database for the evaluation of heart sound algorithms. Physiol Meas 37:2181–2213. https://doi.org/10.1088/0967-3334/37/12/2181

    Article  PubMed  PubMed Central  Google Scholar 

  32. Kambhampati AB, Ramkumar B (2021) Automatic detection and classification of systolic and diastolic profiles of PCG corrupted due to limitations of electronic stethoscope recording. IEEE Sens J 21:5292–5302. https://doi.org/10.1109/JSEN.2020.3028373

    Article  Google Scholar 

  33. Andries Meintjes AL (2018) and ML Fundamental heart sound classification using the continuous wavelet transform and convolutional neural networks. In: IEEE engineering in medicine and biology society. pp 409–412

  34. Abubakar A, Ugail H, Bukar AM (2020) Assessment of human skin burns: a deep transfer learning approach. J Med Biol Eng 40:321–333. https://doi.org/10.1007/s40846-020-00520-z

    Article  Google Scholar 

  35. Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60:84–90. https://doi.org/10.1145/3065386

    Article  Google Scholar 

  36. Raphael C, Briscoe C, Davies J et al (2015) Going deeper with convolutions. In: IEEE conference on computer vision and pattern recognition. pp 1–9

  37. Forman DE, Fleg JL, Kitzman DW et al (2012) 6-min walk test provides prognostic utility comparable to cardiopulmonary exercise testing in ambulatory outpatients with systolic heart failure. J Am Coll Cardiol 60:2653–2661. https://doi.org/10.1016/j.jacc.2012.08.1010

    Article  PubMed  PubMed Central  Google Scholar 

  38. Goetschalckx K, Rademakers F, Bogaert J (2010) Right ventricular function by MRI. Curr Opin Cardiol 25:451–455

    Article  PubMed  Google Scholar 

  39. Saha NM, Barbat JJ, Fedson S et al (2015) Outpatient use of focused cardiac ultrasound to assess the inferior vena cava in patients with heart failure. Am J Cardiol 116:1224–1228. https://doi.org/10.1016/j.amjcard.2015.07.040

    Article  PubMed  Google Scholar 

  40. Levine A, Hecht HS (2015) Cardiac CT angiography in congestive heart failure. J Nucl Med 56:46S-51S. https://doi.org/10.2967/jnumed.114.150441

  41. Dhaliwal AS, Deswal A, Pritchett A et al (2009) Reduction in BNP levels with treatment of decompensated heart failure and future clinical events. J Card Fail 15:293–299. https://doi.org/10.1016/j.cardfail.2008.11.007

    Article  CAS  PubMed  Google Scholar 

  42. Davidson NC, Naas AA, Hanson JK et al (1996) Comparison of atrial natriuretic peptide, B-type natriuretic peptide, and N-terminal proatrial natriuretic peptide as indicators of left ventricular systolic dysfunction. Am J Cardiol 77:828-831

  43. Moriichi A, Cho K, Mizushima M et al (2012) B-type natriuretic peptide levels at birth predict cardiac dysfunction in neonates. Pediatr Int 54:89–93. https://doi.org/10.1111/j.1442-200X.2011.03500.x

    Article  CAS  PubMed  Google Scholar 

Download references

Funding

This study was supported by the National Natural Science Foundation of China (No. 31870980 and No. 31800823).

Author information

Authors and Affiliations

  1. Key Laboratory of Biorheology Science and Technology, Ministry of Education, College of Bioengineering, Chongqing University, 400044, Chongqing, China

    Xiao Chen, Xingming Guo & Chengcong Lv

  2. Department of Radiology, the First Affiliated Hospital of Chongqing Medical University, 400016, Chongqing, China

    Yineng Zheng

Authors
  1. Xiao Chen
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Xingming Guo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yineng Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chengcong Lv
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

XC, YZ ,CL and XG collected the experimental data, reviewed literatures and discussed the method for this study. XC performed the experiments and drafted the manuscript. XG and YZ reviewed and edited the writing. All authors XC, XG, YZ and CL finalized the manuscript for submission. All authors read and approved the final manuscript.

Corresponding author

Correspondence to Xingming Guo.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Ethics approval

This study was performed in line with the principles of the Declaration of Helsinki. Approval was granted by the Ethics Committee of the First Affiliated Hospital of Chongqing Medical University (Protocol no: CYYYLL2018-092, 15 January 2018).

Consent to participate

Informed consent was obtained from all individual participants included in the study.

Consent for publication

Not applicable.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Chen, X., Guo, X., Zheng, Y. et al. Heart function grading evaluation based on heart sounds and convolutional neural networks. Phys Eng Sci Med 46, 279–288 (2023). https://doi.org/10.1007/s13246-023-01216-9

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13246-023-01216-9

Keywords

Search

Navigation