Skip to main content

Advertisement

Springer Nature Link
Log in

Abnormal heart sound detection from unsegmented phonocardiogram using deep features and shallow classifiers

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Phonocardiogram (PCG) is commonly used as a diagnostic tool in ambulatory monitoring in order to evaluate cardiac abnormalities and detect cardiovascular diseases. Although cardiac auscultation is widely used for evaluation of cardiac function, the analysis of heart sound signals mostly depends on the clinician’s experience and skills. There is growing demand for automatic and objective heart sound interpretation techniques. The objective of this study is to develop an automatic classification method for anomaly (binary and multi-class) detection of PCG recordings without any segmentation. A deep neural network (DNN) model is used on the raw data during the extraction of the features of the PCG inputs. Deep feature maps obtained from hierarchically placed layers in DNN are fed to various shallow classifiers for the anomaly detection, including support vector classifier (SVC), k-nearest neighbors (KNN), random forest (RF), gradient boosting (GB) classifier, decision tree (DT) classifier, quadratic discriminant analysis (QDA), and multi-layer perception (MLP). Principal component analysis (PCA) technique is used to reduce the high dimensions of feature maps.Finally, two famous heart sound databases, namely PhysioNet/Computing in Cardiology (CinC) Challenge heart sound database and heart valve disease (HVD) database, are used for evaluation. The databases are significantly different in terms of the tools used for data acquisition, clinical protocols, digital storages and signal qualities, making it challenging to process and analyze. By using the 10-fold cross-validation style, experimental results demonstrate that the proposed deep features with shallow classifiers yield highest performance with accuracy of 99.61% and 99.44% for binary and multi-class classification on the two databases, respectively. The results indicate that our method is effective for the detection of abnormal heart sound signals and outperforms other state-of-the-art methods.

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

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

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
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Data Availability

The datasets used and/or analyzed during in current study are available from the public PhysioNet/CinC Challenge heart sound database [22, 34] and heart valve disease (HVD) database [53].

References

  1. Al-Naami B, Fraihat H, Gharaibeh NY, Al-Hinnawi ARM (2020) A framework classification of heart sound signals in PhysioNet challenge 2016 using high order statistics and adaptive Neuro-Fuzzy inference system. IEEE Access 8:224852–224859

    Article  Google Scholar 

  2. Alkhodari M, Fraiwan L (2021) Convolutional and recurrent neural networks for the detection of valvular heart diseases in phonocardiogram recordings. Comput Methods Prog Biomed 200:105940

    Article  Google Scholar 

  3. Bhatti UA, Huang M, Wu D, Zhang Y, Mehmood A, Han H (2019) Recommendation system using feature extraction and pattern recognition in clinical care systems. Enterp Inf Syst 13(3):329–351

    Article  Google Scholar 

  4. Bhatti UA, Yan Y, Zhou M, Ali S, Hussain A, Qingsong H, Yuan L (2021) Time series analysis and forecasting of air pollution particulate matter (PM 2.5): an SARIMA and factor analysis approach. IEEE Access 9:41019–41031

    Article  Google Scholar 

  5. Bhatti UA, Zeeshan Z, Nizamani MM, Bazai S, Yu Z, Yuan L (2022) Assessing the change of ambient air quality patterns in Jiangsu province of China pre-to post-COVID-19. Chemosphere 288:132569

    Article  Google Scholar 

  6. Biau G, Scornet E (2016) A random forest guided tour. Test 25 (2):197–227

    Article  MathSciNet  MATH  Google Scholar 

  7. Bilal EM (2021) Heart sounds classification using convolutional neural network with 1D-local binary pattern and 1D-local ternary pattern features. Appl Acoust 180:108152

    Article  Google Scholar 

  8. Castro A, Vinhoza TT, Mattos SS, Coimbra MT (2013) Heart sound segmentation of pediatric auscultations using wavelet analysis. In: 35th annual international conference of the IEEE engineering in medicine and biology society, pp 3909-3912

  9. Chawla NV, Bowyer KW, Hall LO, Kegelmeyer WP (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357

    Article  MATH  Google Scholar 

  10. Cheema A, Singh M (2019) An application of phonocardiography signals for psychological stress detection using non-linear entropy based features in empirical mode decomposition domain. Appl Soft Comput 77:24–33

    Article  Google Scholar 

  11. Chen P, Zhang Q (2020) Classification of heart sounds using discrete time-frequency energy feature based on S transform and the wavelet threshold denoising. Biomed Signal Process Control 57:101684

    Article  Google Scholar 

  12. Cömert Z, Akbulut Y, Akpinar MH, Alcin OF, BudakÜ Aslan M, Sengür A (2020) Electrocardiogram beat classification using deep convolutional neural network techniques. Modelling and Analysis of Active Biopotential Signals in Healthcare, Volume 1, 12-1-12-26

  13. Deng SW, Han JQ (2016) Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps. Futur Gener Comput Syst 60:13–21

    Article  Google Scholar 

  14. Deng M, Meng T, Cao J, Wang S, Zhang J, Fan H (2020) Heart sound classification based on improved MFCC features and convolutional recurrent neural networks. Neural Netw 130:22–32

    Article  Google Scholar 

  15. Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, Jimenez-Moreno G (2017) Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors. IEEE Trans Biomed Circuits Syst 12(1):24–34

    Article  Google Scholar 

  16. Fan GF, Yu M, Dong SQ, Yeh YH, Hong WC (2021) Forecasting short-term electricity load using hybrid support vector regression with grey catastrophe and random forest modeling. Util Policy 73:101294

    Article  Google Scholar 

  17. Fan GF, Zhang LZ, Yu M, Hong WC, Dong SQ (2022) Applications of random forest in multivariable response surface for short-term load forecasting. Int J Electr Power Energy Syst 139:108073

    Article  Google Scholar 

  18. Feng W, Dauphin G, Huang W, Quan Y, Bao W, Wu M, Li Q (2019) Dynamic synthetic minority over-sampling tTechnique-based rotation forest for the classification of imbalanced hyperspectral data. IEEE J Sel Top Appl Earth Obs Remote Sens 12(7):2159–2169

    Article  Google Scholar 

  19. Gavrovska A, Zajic G, Bogdanovic V, Reljin I, Reljin B (2016) Paediatric heart sound signal analysis towards classification using multifractal spectra. Physiol Meas 37(9):1556

    Article  MATH  Google Scholar 

  20. Gavrovska A, Zajic G, Bogdanovic V, Reljin I, Reljin B (2017) Identification of s1 and s2 heart sound patterns based on fractal theory and shape context. Complexity 2017

  21. Ghosh SK, Ponnalagu RN, Tripathy RK, Acharya UR (2020) Automated detection of heart valve diseases using chirplet transform and multiclass composite classifier with PCG signals. Comput Biol Med 118:103632

    Article  Google Scholar 

  22. Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PCh, Mark RG, Mietus JE, Moody GB, Peng CK, Stanley HE (2003) PhysioBank, physioToolkit, and physioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):e215-e220

    Google Scholar 

  23. Hassan AR, Siuly S, Zhang Y (2016) Epileptic seizure detection in EEG signals using tunable-Q factor wavelet transform and bootstrap aggregating. Comput Methods Prog Biomed 137:247–259

    Article  Google Scholar 

  24. Huang B, Kunoth A (2013) An optimization based empirical mode decomposition scheme. J Comput Appl Math 240:174–183

    Article  MathSciNet  MATH  Google Scholar 

  25. Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, Liu HH (1998) The empirical mode decomposition and Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings of the Royal Society of London A: Mathematical, Physical and Engineering Sciences. The Royal Society 454 (1971):903–995

    Article  MathSciNet  Google Scholar 

  26. Humayun AI, Ghaffarzadegan S, Ansari MI, Feng Z, Hasan T (2020) Towards domain invariant heart sound abnormality detection using learnable filterbanks. IEEE J Biomed Health Inform 24(8):2189–2198

    Article  Google Scholar 

  27. Khan KN, Khan FA, Abid A, Olmez T, Dokur Z, Khandakar A, Khan MS (2021) Deep learning based classification of unsegmented phonocardiogram spectrograms leveraging transfer learning. Physiol Meas 42(9):095003

    Article  Google Scholar 

  28. Kobat MA, Dogan S (2021) Novel three kernelled binary pattern feature extractor based automated PCG sound classification method. Appl Acoust 179:108040

    Article  Google Scholar 

  29. Kramer O (2013) K-nearest neighbors. In: Dimensionality reduction with unsupervised nearest neighbors, pp 13-23. Springer, Berlin, Heidelberg

  30. Krishnan PT, Balasubramanian P, Umapathy S (2020) Automated heart sound classification system from unsegmented phonocardiogram (PCG) using deep neural network. Phys Eng Sci Med 43:505–515

    Article  Google Scholar 

  31. Lau KW, Wu QH (2003) Online training of support vector classifier. Pattern Recog 36(8):1913–1920

    Article  MATH  Google Scholar 

  32. Li J, Ke L, Du Q (2019) Classification of heart sounds based on the wavelet fractal and twin support vector machine. Entropy 21(5):472

    Article  MathSciNet  Google Scholar 

  33. Liang QZ, Guo XM, Zhang WY, Dai WD, Zhu XH (2015) Identification of heart sounds with arrhythmia based on recurrence quantification analysis and Kolmogorov entropy. Journal Med Biol Eng 35(2):209–217

    Article  Google Scholar 

  34. Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, Syed Z (2016) An open access database for the evaluation of heart sound algorithms. Physiol Meas 37(12):2181

    Article  Google Scholar 

  35. Liu L, Wang H, Wang Y, Tao T, Wu X (2010) Feature analysis of heart sound based on the improved Hilbert-Huang transform. In: 3rd IEEE International Conference on Computer Science and Information Technologyb, pp 378–381

  36. Messner E, Zohrer M, Pernkopf F (2018) Heart sound segmentation-an event detection approach using deep recurrent neural networks. IEEE Trans Biomed Eng 65(9):1964–1974

    Article  Google Scholar 

  37. Murat F, Yildirim O, Talo M, Demir Y, Tan RS, Ciaccio EJ, Acharya UR (2021) Exploring deep features and ECG attributes to detect cardiac rhythm classes. Knowl-Based Syst:107473

  38. Murtagh F (1991) Multilayer perceptrons for classification and regression. Neurocomputing 2(5-6):183–197

    Article  MathSciNet  Google Scholar 

  39. Natekin A, Knoll A (2013) Gradient boosting machines, a tutorial. Front Neurorobot 7:21

    Article  Google Scholar 

  40. Nawaz SA, Li J, Bhatti UA, Bazai SU, Zafar A, Bhatti MA, Shoukat MU (2021) A hybrid approach to forecast the COVID-19 epidemic trend. Plos One 16(10):e0256971

    Article  Google Scholar 

  41. Nishad A, Pachori RB, Acharya UR (2018) Application of TQWT based filter-bank for sleep apnea screening using ECG signals. J Ambient Intell Humanized Comput. https://doi.org/10.1007/s12652-018-0867-3

  42. Noman F, Salleh SH, Ting CM, Samdin SB, Ombao H, Hussain H (2019) A Markov-switching model approach to heart sound segmentation and classification. IEEE J Biomed Health Inform 24(3):705–716

    Article  Google Scholar 

  43. Oh SL, Jahmunah V, Ooi CP, Tan RS, Ciaccio EJ, Yamakawa T, Acharya UR (2020) Classification of heart sound signals using a novel deep WaveNet model. Comput Methods Prog Biomed 196:105604

    Article  Google Scholar 

  44. Oliveira J, Renna F, Coimbra M (2019) A subject-driven unsupervised hidden semi-Markov model and Gaussian mixture model for heart sound segmentation. IEEE J Sel Top Sig Process 13(2):323–331

    Article  Google Scholar 

  45. Park C, Looney D, Van Hulle MM, Mandic DP (2011) The complex local mean decomposition. Neurocomputing 74(6):867–875

    Article  Google Scholar 

  46. Patidar S, Pachori RB, Upadhyay A, Acharya UR (2017) An integrated alcoholic index using tunable-Q wavelet transform based features extracted from EEG signals for diagnosis of alcoholism. Appl Soft Comput 50:71–78

    Article  Google Scholar 

  47. Renna F, Oliveira JH, Coimbra MT (2019) Deep convolutional neural networks for heart sound segmentation. IEEE J Biomed Health Inform 23(6):2435–2445

    Article  Google Scholar 

  48. Rivera WA, Xanthopoulos P (2016) A priori synthetic over-sampling methods for increasing classification sensitivity in imbalanced data sets. Expert Syst Appl 66:124–135

    Article  Google Scholar 

  49. Safavian SR, Landgrebe D (1991) A survey of decision tree classifier methodology. IEEE Transactions on Systems. IEEE Trans Syst Man Cybern 21 (3):660–674

    Article  Google Scholar 

  50. Salman AH, Ahmadi N, Mengko R, Langi AZ, Mengko TL (2016) Empirical mode decomposition (EMD) based denoising method for heart sound signal and its performance analysis. Int J Electr Comput Eng 6(5):1–8

    Google Scholar 

  51. Selesnick I (2011) Wavelet transform with tunable Q-factor. IEEE Trans Sig Process 59(8):3560–3575

    Article  MathSciNet  MATH  Google Scholar 

  52. Soares E, Angelov P, Gu X (2020) Autonomous Learning Multiple-Model zero-order classifier for heart sound classification. Appl Soft Comput 94:106449

    Article  Google Scholar 

  53. Son GY, Kwon S (2018) Classification of heart sound signal using multiple features. Appl Sci 8(12):2344

    Article  Google Scholar 

  54. Springer DB, Tarassenko L, Clifford GD (2015) Logistic regression-HSMM-based heart sound segmentation. IEEE Trans Biomed Eng 63(4):822–832

    Google Scholar 

  55. Srivastava S, Gupta MR, Frigyik BA (2007) Bayesian quadratic discriminant analysis. J Mach Learn Res 8(6):1277–1305

    MathSciNet  MATH  Google Scholar 

  56. Talo M (2019) Automated classification of histopathology images using transfer learning. Artif Intell Med 101:101743

    Article  Google Scholar 

  57. Tang H, Chen H, Li T (2017) Discrimination of aortic and pulmonary components from the second heart sound using respiratory modulation and measurement of respiratory split. Appl Sci 7(7):690

    Article  Google Scholar 

  58. Thiyagaraja SR, Dantu R, Shrestha PL, Chitnis A, Thompson MA, Anumandla PT, Dantu S (2018) A novel heart-mobile interface for detection and classification of heart sounds. Biomed Signal Process Control 45:313–324

    Article  Google Scholar 

  59. Tuncer T, Dogan S, Tan RS, Acharya UR (2021) Application of Petersen graph pattern technique for automated detection of heart valve diseases with PCG signals. Inf Sci 565:91–104

    Article  MathSciNet  Google Scholar 

  60. Varghees VN, Ramachandran KI (2017) Effective heart sound segmentation and murmur classification using empirical wavelet transform and instantaneous phase for electronic stethoscope. IEEE Sensors J 17(12):3861–3872

    Article  Google Scholar 

  61. Wang Q, Zhou X, Wang C, Liu Z, Huang J, Zhou Y, Cheng JZ (2019) WGAN-based synthetic minority over-sampling technique: improving semantic fine-grained classification for lung nodules in CT images. IEEE Access 7:18450–18463

    Article  Google Scholar 

  62. Xiao B, Xu Y, Bi X, Zhang J, Ma X (2019) Heart sounds classification using a novel 1-D convolutional neural network with extremely low parameter consumption. Neurocomputing 392(7):153–159

    Google Scholar 

  63. Ye J, Janardan R, Li Q (2004) Two-dimensional linear discriminant analysis. Advances Neural Inf Process Syst 17:1569–1576

    Google Scholar 

  64. Zabihi M, Rad AB, Kiranyaz S, Gabbouj M, Katsaggelos AK (2016) Heart sound anomaly and quality detection using ensemble of neural networks without segmentation. In: 2016 Computing in Cardiology Conference, pp 613–616

  65. Zeeshan Z, Bhatti UA, Memon WH, Ali S, Nawaz SA, Nizamani MM, Shoukat MU (2021) Feature-based multi-criteria recommendation system using a weighted approach with ranking correlation. Intell Data Anal 25 (4):1013–1029

    Article  Google Scholar 

  66. Zeng W, Lin Z, Yuan C, Wang Q, Liu F, Wang Y (2021) Detection of heart valve disorders from PCG signals using TQWT, FA-MVEMD, Shannon energy envelope and deterministic learning. Artif Intell Rev 54(8):6063–6100

    Article  Google Scholar 

  67. Zeng W, Yuan J, Yuan C, Wang Q, Liu F, Wang Y (2021) A new approach for the detection of abnormal heart sound signals using TQWT, VMD and neural networks. Artif Intell Rev 54(3):1613–1647

    Article  Google Scholar 

  68. Zhang WJ, Han JQ, Deng SW (2019) Abnormal heart sound detection using temporal quasi-periodic features and long short-term memory without segmentation. Biomed Sig Process Control 53:101560

    Article  Google Scholar 

  69. Zhang D, He J, Jiang Y, Du M (2011) Analysis and classification of heart sounds with mechanical prosthetic heart valves based on Hilbert-Huang transform. Int J Cardiol 151(1):126–127

    Article  Google Scholar 

  70. Zhao L, Wei S, Tang H, Liu C (2016) Multivariable fuzzy measure entropy analysis for heart rate variability and heart sound amplitude variability. Entropy 18(12):430

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Natural Science Foundation of Fujian Province (Grant no. 2022J011146).

Author information

Authors and Affiliations

  1. School of Physics and Mechanical and Electrical Engineering, Longyan University, Longyan, 364012, People’s Republic of China

    Yang Chen, Bo Su & Wei Zeng

  2. School of Mechanical Engineering and Automation, Fuzhou University, Fuzhou, 350116, People’s Republic of China

    Yang Chen, Bo Su & Wei Zeng

  3. Department of Mechanical, Industrial and Systems Engineering, University of Rhode Island, Kingston, Rhode Island, 02881, USA

    Chengzhi Yuan

  4. School of Control Science and Engineering, Shandong University, Jinan, 250061, People’s Republic of China

    Bing Ji

Authors
  1. Yang Chen
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Bo Su
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Wei Zeng
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Chengzhi Yuan
    View author publications

    You can also search for this author inPubMed Google Scholar

  5. Bing Ji
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Wei Zeng.

Ethics declarations

Ethics approval

There is no issue with Ethical approval and Informed consent.

Conflict of Interests

There is no conflict of interest.

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, Y., Su, B., Zeng, W. et al. Abnormal heart sound detection from unsegmented phonocardiogram using deep features and shallow classifiers. Multimed Tools Appl 82, 26859–26883 (2023). https://doi.org/10.1007/s11042-022-14315-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-022-14315-8

Keywords