Principal component analysis-based features generation combined with ellipse models-based classification criterion for a ventricular septal defect diagnosis system

  • Shuping SunEmail author
  • Haibin WangEmail author
Scientific Paper


In this study, a simple and efficient diagnostic system, which adopts a novel methodology consisting of principal component analysis (PCA)-based feature generation and ellipse models-based classification criterion, is proposed for the diagnosis of a ventricular septal defect (VSD). The three stages corresponding to the diagnostic system implementation are summarized as follows. In stage 1, the heart sound is collected by 3M-3200 electronic stethoscope and is preprocessed using the wavelet decomposition. In stage 2, the PCA-based diagnostic features, [\(y_{1}, y_{2}\)], are generated from time-frequency feature matrix (\({\text{TFFM}}\)). In the matrix TFFM, the time domain features \([T_{12}, T_{11}]\) are firstly extracted from the time domain envelope \(E_{\text{T}}\) for the filtered heart sound signal \(X_{\text{T}}\), and frequency domain features, \([F_{\text{G}}, F_{\text{W}}]\), are subsequently extracted from a frequency domain envelope (\(E_{\text {F}}\)) for each heart sound cycle automatically segmented via the short time modified Hilbert transform (STMHT). In stage 3, support vector machines-based classification boundary curves for the dataset \([y_{{1}}, y_{{2}}]\) are first generated, and least-squares-based ellipse models are subsequently built for the classification boundary curve. Finally, based on the ellipse models, the classification criterion is defined for the diagnosis of VSD sounds. The proposed diagnostic system is validated by sounds from the internet and by sounds from clinical heart diseases. Moreover, comparative analysis to validate the usefulness of the proposed diagnostic system, mitral regurgitation and aortic stenosis sounds are used as examples for detection. As a result, the higher classification accuracy, which is achieved by this study compared to the other methods, is \(95.5\%\), \(92.1\%\), \(96.2\%\) and \(99.0\%\) for diagnosing small VSD, moderate VSD, large VSD and normal sounds, respectively.


VSD STMHT PCA Classification boundary curves Ellipse model 



This study was funded by the National Natural Science Foundation of China (Grant No. 61571371).

Compliance with ethical standards

Conflict of interest

We declare that we have no conflict of interest.

Ethical approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards.

Informed consent

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


  1. 1.
    John Mersch F (2016) Ventricular septal defect: congenital heart problems, murmurs.,
  2. 2.
    Bhatikar SR, DeGroff C, Mahajan RL (2005) A classifier based on the artificial neural network approach for cardiologic auscultation in pediatrics. Artif Intell Med 33(3):251. CrossRefGoogle Scholar
  3. 3.
    Higuchi K, Sato K, Makuuchi H, Furuse A, Takamoto S, Takeda H (2006) Automated diagnosis of heart disease in patients with heart murmurs: application of a neural network technique. J Med Eng Technol 30(2):61CrossRefGoogle Scholar
  4. 4.
    Choi S, Jiang Z (2010) Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique. Comput Biol Med 40(1):8. CrossRefGoogle Scholar
  5. 5.
    Chauhan S, Wang P, Sing C, Anantharaman V (2008) A computer-aided MFCC-based HMM system for automatic auscultation. Comput Biol Med 38:221. CrossRefPubMedGoogle Scholar
  6. 6.
    Patidar S, Pachori RB, Garg N (2015) Automatic diagnosis of septal defects based on tunable-Q wavelet transform of cardiac sound signals. Expert Syst Appl 42(7):3315. CrossRefGoogle Scholar
  7. 7.
    Sun S, Wang H, Jiang Z, Fang Y, Tao T (2014) Segmentation-based heart sound feature extraction combined with classifier models for a VSD diagnosis system. Expert Syst Appl 41(4, Part 2), 1769. CrossRefGoogle Scholar
  8. 8.
    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. CrossRefGoogle Scholar
  9. 9.
    Karar ME, El-khafif S, El-brawany M (2017) Automated diagnosis of heart sounds using rule-based classification tree. J Med Syst.
  10. 10.
    Kalkbrenner C, Eichenlaub M, Rüdiger S, Kropf-Sanchen C, Rottbauer W, Brucher R (2018) Apnea and heart rate detection from tracheal body sounds for the diagnosis of sleep-related breathing disorders. Med Biol Eng Comput 3:1–2. CrossRefGoogle Scholar
  11. 11.
    Beritelli F, Capizzi G, Scaglione F (2018) Automatic heart activity diagnosis based on Gram polynomials and probabilistic neural networks. Biomed Eng Lett 8:77–85CrossRefGoogle Scholar
  12. 12.
    Guo HW, Huang YS, Lin CH, Chien JC, Haraikawa K, Shieh JS (2016) Heart rate variability signal features for emotion recognition by using principal component analysis and support vectors machine. In 2016 IEEE 16th international conference on bioinformatics and bioengineering (BIBE) pp. 274–277.
  13. 13.
    Motin MA (2018) Principal component analysis: a novel approach for extracting respiratory rate and heart rate from photoplethysmographic. Signal 22(3):766Google Scholar
  14. 14.
    IEEE International Conference on Intelligent Computing and Information Systems (2017). In: The 8th IEEE international conference on intelligent computing and information systems (ICICIS 2017) 5(Icicis), p 154Google Scholar
  15. 15.
    Mohseni SS (2016) Heart arrhythmias classification via a sequential classifier using neural network , principal component analysis and heart rate variation. In IEEE 8th international conference on intelligent systems heart. pp 715–722Google Scholar
  16. 16.
    Kavitha R, Kannan E (2016) An efficient framework for heart disease classification using feature extraction and feature selection technique in data mining. In 1st international conference on emerging trends in engineering, technology and science, ICETETS 2016 - proceedings.
  17. 17.
    Palaniappan R, Sundaraj K, Ahamed NU (2013) Machine learning in lung sound analysis: a systematic review. Biocybern Biomed Eng 33(3):129. CrossRefGoogle Scholar
  18. 18.
    Radüntz T, Scouten J, Hochmuth O, Meffert B (2017) Automated EEG artifact elimination by applying machine learning algorithms to ICA-based features. J Neural Eng 14(4):046004. CrossRefPubMedGoogle Scholar
  19. 19.
    Chen Y, Luo Y, Huang W, Hu D, Qin Zheng R, Zhen Cong S, Kun Meng F, Yang H, Jun Lin H, Sun Y, Yan Wang X, Wu T, Ren J, Pei SF, Zheng Y, He Y, Hu Y, Yang N, Yan H (2017) Machine-learning-based classification of real-time tissue elastography for hepatic fibrosis in patients with chronic hepatitis B. Comput Biol Med 89:18–23. CrossRefPubMedGoogle Scholar
  20. 20.
    Du J, Xu J, Song H, Liu X, Tao C (2017) Optimization on machine learning based approaches for sentiment analysis on HPV vaccines related tweets. J Biomed Semant 8(1):1. CrossRefGoogle Scholar
  21. 21.
    Joutsijoki H, Haponen M, Rasku J, Aalto-Setala K, Juhola M (2016) Machine learning approach to automated quality identification of human induced pluripotent stem cell colony images. Comput Math Methods Med 2016:15. CrossRefGoogle Scholar
  22. 22.
    Vapnik VN (1999) An overview of statistical learning theory. IEEE Trans Neural Networks 10(5):988CrossRefGoogle Scholar
  23. 23.
    Mehta S, Lingayat N (2008) SVM-based algorithm for recognition of QRS complexes in electrocardiogram. IRBM 29(5):310. CrossRefGoogle Scholar
  24. 24.
    Akay MF (2009) Support vector machines combined with feature selection for breast cancer diagnosis. Expert Syst Appl 36(2):3240. CrossRefGoogle Scholar
  25. 25.
    Lokhov PG, Kharybin ON, Archakov AI (2012) Diagnosis of lung cancer based on direct-infusion electrospray mass spectrometry of blood plasma metabolites. Int J Mass Spectrom 309:200. CrossRefGoogle Scholar
  26. 26.
    Wu J, Ji Y, Zhao L, Ji M, Ye Z, Li S (2016) A mass spectrometric analysis method based on PPCA and SVM for Early Detection of Ovarian Cancer. Comput Math Methods Med 2016:6169249. CrossRefPubMedPubMedCentralGoogle Scholar
  27. 27.
    Yu B, Gao JR, Ding D, Zeng X, Pan DZ (2014) Accurate lithography hotspot detection based on principal component analysis-support vector machine classifier with hierarchical data clustering. J Micro/Nanolithogr MEMS MOEMS 14(1):011003. CrossRefGoogle Scholar
  28. 28.
    Khedher L, Ramírez J, Górriz JM, Brahim A, Segovia F (2015) Early diagnosis of Alzheimer’s disease based on partial least squares, principal component analysis and support vector machine using segmented MRI images. Neurocomputing 151(P1):139. CrossRefGoogle Scholar
  29. 29.
    Chen Y, Yang M, Chen X, Liu B, Wang H, Wang S (2016) Sensorineural hearing loss detection via discrete wavelet transform and principal component analysis combined with generalized eigenvalue proximal support vector machine and Tikhonov regularization. Multimedia Tools Appl. CrossRefGoogle Scholar
  30. 30.
    Yang HX, Fu HB, Wang HD, Jia JW, Sigrist MW, Dong FZ (2016) Laser-induced breakdown spectroscopy applied to the characterization of rock by support vector machine combined with principal component analysis. Chin Phys B 25(6):065201. CrossRefGoogle Scholar
  31. 31.
    Jung H, Jo H, Kim S, Lee K, Choe J (2018) Geological model sampling using PCA-assisted support vector machine for reliable channel reservoir characterization. J Petrol Sci Eng 167:396. CrossRefGoogle Scholar
  32. 32.
    3MCompany (2014) 3m health care company.
  33. 33.
  34. 34.
  35. 35.
    Sound MH (2012) Murmur Library. University of michigan heart sound and murmur library.
  36. 36.
    Coviello JS (2015) Auscultation Skills Google Scholar
  37. 37.
    Nilsson M, Funk P (2006) Clinical decision-support for diagnosing stress-related disorders by applying psychophysiological medical knowledge to an instance-based learning system. Artif Intell Med 36(2):159. CrossRefGoogle Scholar
  38. 38.
    Choi S, Shin Y, Park HK (2011) Selection of wavelet packet measures for insufficiency murmur identification. Expert Syst Appl 38(4):4264. CrossRefGoogle Scholar
  39. 39.
    Sun S, Jiang Z, Wang H, Fang Y (2014) Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified hilbert transform. Comput Methods Programs Biomed 114(3):219. CrossRefGoogle Scholar
  40. 40.
    Ali MN, El-Dahshan ESA, Yahia AH (2017) Denoising of heart sound signals using discrete wavelet transform. Circuits Syst Signal Process 36(11):4482. CrossRefGoogle Scholar
  41. 41.
    Hamidi M, Ghassemian H, Imani M (2018) Classification of heart sound signal using curve fitting and fractal dimension. Biomed Signal Process Control 39:351. CrossRefGoogle Scholar
  42. 42.
    Sweldens WW (1996) What next. In Proceedings of the IEEE 84, 1996 p. 680–685CrossRefGoogle Scholar
  43. 43.
    Mallat S (1999) A wavelet tour of signal processing. Academic Press, San DiegoGoogle Scholar
  44. 44.
    Sun S, Jiang Z, Wang H, Fang Y (2014) Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform. Comput Methods Programs Biomed 114(3):219. CrossRefPubMedGoogle Scholar
  45. 45.
    Shuping Sun HW, Fang Y, Jiang Z Freqeuncy features matrix-based for heart sound analysis and detection. Comput Methods Programs Biomed (Unpublished results)Google Scholar
  46. 46.
    Giri D, Rajendra Acharya U, Martis RJ, Vinitha Sree S, Lim TC, Ahamed T, Suri JS (2013) Automated diagnosis of coronary artery disease affected patients using LDA, PCA, ICA and discrete wavelet transform. Knowledge-Based Syst 37:274. CrossRefGoogle Scholar
  47. 47.
    Lee J, Jun CH (2013) PCA-based high-dimensional noisy data clustering via control of decision errors. Knowledge-Based Syst 37:338. CrossRefGoogle Scholar
  48. 48.
    Shilaskar S, Ghatol A (2013) Feature selection for medical diagnosis: evaluation for cardiovascular diseases. Expert Syst Appl 40(10):4146. CrossRefGoogle Scholar
  49. 49.
    Zhu B, Ding Y, Hao K (2014) Multiclass maximum margin clustering via immune evolutionary algorithm for automatic diagnosis of electrocardiogram arrhythmias. Appl Math Comput 227:428. CrossRefGoogle Scholar
  50. 50.
    Johnson RA, Wichern DW (2007) Applied multivariate statistical analysis, 6th edn. Pearson Prentice Hall, Upper Saddle River.

Copyright information

© Australasian College of Physical Scientists and Engineers in Medicine 2018

Authors and Affiliations

  1. 1.Department of Electronic and Electric EngineeringNanyang Institute of TechnologyNanyangChina
  2. 2.School of Electrical and Information EngineeringXihua UniversityChengduChina

Personalised recommendations