Estimation and Evaluation of New Features from Phonocardiogram for Detecting Cardiovascular Abnormalities

Document Type : Original Article (s)

Authors

1 MSc Student, Department of Bioelectrics and Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

2 Associate Professor, Department of Bioelectrics and Biomedical Engineering, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

3 Professor, Cardiac Rehabilitation Research Center, Cardiovascular Research Institute, Isfahan University of Medical Sciences, Isfahan, Iran

4 PhD Student, Department of Biomedical Engineering, Student Research Committee, School of Advanced Technologies in Medicine, Isfahan University of Medical Sciences, Isfahan, Iran

Abstract

Background: In the world, cardiovascular diseases are the major cause of death, as 31% of global mortality is from them. Due to problems such as the lack of technologies such as echocardiography, and limited access to cardiologists in deprived areas, automatic methods for detecting heart abnormalities in phonocardiogram (PCG) are used.Methods: In this study, to distinguish between normal and abnormal cases, three categories of features in PCG were estimated and evaluated. First, the extraction of the heart rate and heart rate variability; second, some of the features used in speech analysis and pattern recognition; and third, the time center, the frequency center, and the frequency variance of the signal. Some methods were proposed for extracting desired features, and the data were analyzed using t-test.Findings: The results of evaluation of the 10 proposed features, with the p-value of less than 0.010, showed that 8 features had significant distinction to detect abnormal cases from the normal ones.Conclusion: Regarding the patterns of the extracted features, the distinction between normal and abnormal signals was observed, which can be used to classify PCGs. Moreover, in the future, new features can be extracted from these patterns using some other analysis such as correlation.

Keywords

References

  1. World Health Organization. Cardiovascular diseases (CVDs) [Online]. [cited 2017 May 17]; Available from: URL: https://www.who.int/en/news-room/fact-sheets/detail/cardiovascular-diseases-(cvds)
  2. Liu C, Springer D, Li Q, Moody B, Juan RA, Chorro FJ, et al. An open access database for the evaluation of heart sound algorithms. Physiol Meas 2016; 37(12): 2181-213.
  3. Perez-Guzman RE, Garcia-Bermudez R, Rojas-Ruiz F, Cespedes-Perez A, Ojeda-Riquenes Y. Evaluation of algorithms for automatic classification of heart sound signals. Proceedings of the 5th International Conference on Bioinformatics and Biomedical Engineerin; 2017 26-28 Apr; Granda, Spain. Cham, Switzerland: Springer International Publishing; 2017 p. 536-45.
  4. Balili CC, Sobrepena CC, Naval PC. Classification of heart sounds using discrete and continuous wavelet transform and random forests. Proceedings of 3rd IAPR Asian Conference on Pattern Recognition (ACPR); 2015 Nov 3-6; Kuala Lumpur, Malaysia. p. 655-9.
  5. Moukadem A, Dieterlen A, Brandt C. Shannon Entropy based on the S-Transform Spectrogram applied on the classification of heart sounds. Proceedings of 2013 IEEE International Conference on Acoustics, Speech and Signal; 2013 May 26-31; Vancouver, BC, Canada. p. 704-8.
  6. Potes C, Parvaneh S, Rahman A, Conroy B. Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds. Proceedings of the 2016 Computing in Cardiology Conference (CinC); 2016 Sep 11-14; Vancouver, BC, Canada. p. 621-4.
  7. Godino-Llorente JI, Gomez-Vilda P. Automatic detection of voice impairments by means of short-term cepstral parameters and neural network based detectors. IEEE Transactions on Biomedical Engineering 2004; 51(2): 380-4.
  8. Homsi MN, Medina N, Hernandez M, Quintero N, Perpinan G, Quintana A, et al. Automatic heart sound recording classification using a nested set of ensemble algorithms. Proceedings of the 2016 Computing in Cardiology Conference (CinC); 2016 Sep 11-14; Vancouver, BC, Canada. p. 817-20.
  9. Goda MA., Hajas P. Morphological determination of pathological PCG signals by time and frequency domain analysis. Proceedings of the 2016 Computing in Cardiology Conference (CinC); 2016 Sep 11-14; Vancouver, BC, Canada. p. 1133-6.
  10. Flandrin P. Time-Frequency/Time-Scale Analysis. vol. 10. Wavelet Analysis and Its Applications. 1st ed. Cambridge, MA: Academic Press; 1998.
  11. Debbal SM, Bereksi-Reguig F. Time-frequency analysis of the first and the second heartbeat sounds. Appl Math Comput 2007; 184(2): 1041-52.
  12. Clifford GD, Liu C, Moody B, Springer D, Silva I, Li Q, et al. Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016. Proceedings of the 2016 Computing in Cardiology Conference (CinC); 2016 Sep 11-14; Vancouver, BC, Canada. p. 609-12.
  13. Springer DB, Brennan T, Ntusi N, Abdelrahman HY, Zuhlke LJ, Mayosi BM, et al. Automated signal quality assessment of mobile phone-recorded heart sound signals. J Med Eng Technol 2016; 40(7-8): 342-55.
  14. Zali A, Arefian N. Heart rate variability. Pajouhesh Dar Pezeshki 2012; 36(3): 163-6. [In Persian].
  15. Schmidt SE, Holst-Hansen C, Graff C, Toft E, Struijk JJ. Segmentation of heart sound recordings by a duration-dependent hidden Markov model. Physiol Meas 2010; 31(4): 513-29.
  16. Kong J. A study on jitter, shimmer and F0 of Mandarin infant voice by developing an applied method of voice signal processing. Proceedings of the 2008 Congress on Image and Signal Processing; Sanya, Hainan, China. p. 314-8.
  17. Zhao Z, Shen Q, Ren F. Heart sound biometric system based on marginal spectrum analysis. Sensors (Basel) 2013; 13(2): 2530-51.
  18. Wilks' Lambda: Simple Definition [Online]. [cited 2017 Dec 26]; Available from: URL: https://www.statisticshowto.datasciencecentral.com/wilks-lambda
Journal of Isfahan Medical School
Volume 36, Issue 506 - Serial Number 506
November and December 2019
Pages 1444-1449

Files

History

  • Receive Date: 16 August 2018
  • Revise Date: 27 May 2024
  • Accept Date: 06 April 2022

Share

How to cite

Statistics