Spectrum Characteristics Analysis and Recognition of CHD Heart Sound in Five Auscultation Locations

Sheng MIAO¹, Jian’e Dong^1, , Jingyu Hou² and Zhong Lihui¹

¹Bigdata and Intelligence Engineering College of Southwest Forestry University, Kunming650224, China

²School of Information Technology, Deakin University, Victoria, Australia

Cite this paper:
Sheng MIAO, Jian’e Dong, Jingyu Hou and Zhong Lihui. Spectrum Characteristics Analysis and Recognition of CHD Heart Sound in Five Auscultation Locations. Journal of Biomedical Engineering and Technology. 2020; 8(1):14-24. doi: 10.12691/jbet-8-1-3

Abstract

Cardiac Auscultation is widely used in the diagnosis of congenital heart disease (CHD) due to its non-invasive and cost-effective procedure. Heart sound analysis can provide effective auxiliary diagnosis information and aid in automatically screening patients. However, there are different signal spectrum characteristics in different auscultation locations, and there are no unified standards in the selection of auscultation locations during the heart sound analysis. This paper addresses the problem of auscultation locations and the selection of spectrum characteristics in the heart sound identification of CHD patients. 385 cases of normal and CHD heart sound signals were used to extract three groups of representative spectral features: Power Spectral Density (PSD), Mel-Frequency Cepstrum Coefficients (MFCCs) and Instantaneous Frequency Cumulative(IFC) from five different auscultation locations which are Aortic area(A), Pulmonic area(P), Tricuspid area(T), Mitral area(M), and Second aortic valve area(E). Significance detections based on p-value and Gaussian kernel support vector machine (SVM) were used to test these spectrum characteristics in five auscultation locations. The results show that the spectrum energy and the difference of auscultation areas concentrated within the frequency range of 20-150Hz. There is no statistical significance in terms of the spectrum characteristics of CHD in area A (p>0.05) compared with the statistical significance in other auscultation areas (p<0.01). The classification performance of the SVM method that uses spectrum characteristics of area E was the best overall. The experiment and analysis results show that, in CHD heart sound recognition, E-area signals have the best recognition effect, signals from TMP areas could be used as a reference, and A-area signals should be used with cautions. This discovery provides a practical guide to the clinical auscultation and signal processing of Congenital Heart Disease.

Keywords:
Heart Sound (HS) Congenital Heart Disease (CHD) auscultation locations spectrum analysis signal processing

This work is licensed under a Creative Commons Attribution 4.0 International License. To view a copy of this license, visit http://creativecommons.org/licenses/by/4.0/

References:

[1]	Azra, Saeidi, Farshad, Almasganj. 3D heart sound source localization via combinational subspace methods for long-term heart monitoring. Biomedical Signal Processing & Control. 2017; 31: 434-43.
[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. Physiological Measurement. 2016; 37(12): 2181-213.
[3]	Schmidt SE, Holst-Hansen C, Hansen J, Toft E, Struijk JJ. Acoustic Features for the Identification of Coronary Artery Disease. IEEE Transactions on Biomedical Engineering. 2015; 62(11): 2611-9.
[4]	Clifford GD, Liu C, Moody BE, Roig JM, Mark RG. Recent advances in heart sound analysis. Physiological Measurement. 2017; 38(8):E10.
[5]	E C, FH B, SA C, MWM dL, L S, TL G. Newborn pulse oximetry screening in the context of a high antenatal detection rate for critical congenital heart disease. Acta Paediatrica. 2019.
[6]	Vlachos A, Osorio DS, Atsidaftos E, Kang J, Lababidi ML, Seiden HS, et al. Increased Prevalence of Congenital Heart Disease in Children With Diamond Blackfan Anemia Suggests Unrecognized Diamond Blackfan Anemia as a Cause of Congenital Heart Disease in the General Population: A Report of the Diamond Blackfan Anemia Registry. circulation genomic & precision medicine. 2018; 11(5): e002044.
[7]	Li Q, Zhu W, Zhang B, Wu Y, Yuan Y, Zhang H, et al. The MALAT1 gene polymorphism and its relationship with the onset of congenital heart disease in Chinese. Bioscience Reports. 2018; 38(3).
[8]	Fredriksen P, Ingjer E, Thaulow E. Physical activity in children and adolescents with congenital heart disease. Aspects of measurements with an activity monitor. Cardiology in the Young. 2000; 10(2): 98-106.
[9]	Lau I, Sun Z. Three-dimensional printing in congenital heart disease: A systematic review. Journal of Medical Radiation Sciences. 2018.
[10]	Springer DB, Tarassenko L, Clifford GD. Logistic Regression-HSMM-Based Heart Sound Segmentation. IEEE Transactions on Biomedical Engineering. 2016; 63(4): 822-32.
[11]	Tsao Y, Lin T-H, Chen F, Chang Y-F, Cheng C-H, Tsai K-H. Robust S1 and S2 heart sound recognition based on spectral restoration and multi-style training. Biomedical Signal Processing and Control. 2019; 49: 173-80.
[12]	Thiyagaraja SR, Ram D, Shrestha PL, Anurag C, Thompson MA, Anumandla PT, et al. A novel heart-mobile interface for detection and classification of heart sounds. Biomedical Signal Processing & Control. 2018; 45: 313-24.
[13]	Fahad HM, Ghani Khan MU, Saba T, Rehman A, Iqbal S, Diaspro A. Microscopic abnormality classification of cardiac murmurs using ANFIS and HMM. Microscopy Research & Technique. 2018.
[14]	Langley P, Murray A. Heart sound classification from unsegmented phonocardiograms. Physiological Measurement. 2017; 38(8).
[15]	Liu Y, Guo X, Zheng Y. An Automatic Approach Using ELM Classifier for HFpEF Identification Based on Heart Sound Characteristics. Journal of Medical Systems. 2019.
[16]	Zhang W, Han J, Deng S. Heart sound classification based on scaled spectrogram and tensor decomposition. Expert Systems with Applications. 2017; 84: 220-31.
[17]	Whitaker BM, Suresha PB, Liu C, Clifford G, Anderson D. Combining sparse coding and time-domain features for heart sound classification. Physiological Measurement. 2017.
[18]	Mallinson. A survey into paramedic accuracy in identifying the correct anatomic locations for cardiac auscultation. British Paramedic Journal. 2017; 2(2): 5.
[19]	Kang S, Doroshow R, Mcconnaughey J, Shekhar R. Automated Identification of Innocent Still's Murmur in Children. IEEE Transactions on Biomedical Engineering. 2017; 64(6): 1326-34.
[20]	Dominguez-Morales JP, Jimenez-Fernandez AF, Dominguez-Morales MJ, Jimenez-Moreno G. Deep Neural Networks for the Recognition and Classification of Heart Murmurs Using Neuromorphic Auditory Sensors. IEEE Transactions on Biomedical Circuits & Systems. 2017: 1-11.
[21]	Kouras N, Benidir M, Boutana D, editors. The Empirical Mode Decomposition and the SVD for Abnormal Heart Sound Signals detection and Time-Frequency Analysis. Iet International Conference on Intelligent Signal Processing 2016: IET.
[22]	Teo SK, Bo Y, Ling F, Yi S, editors. Power Spectrum Analysis for Classification of Heart Sound Recording. Computing in Cardiology Conference; 2016.
[23]	Jurak. Heart sounds analysis using probability assessment. Physiological Measurement. 2017; vol. 38, no. 8, :pp. 1685-700.
[24]	Chen W, Zhao Y, Lei S, Zhao Z, Pan M. [Study of biometric identification of heart sound base on Mel-Frequency cepstrum coefficient]. Journal of Biomedical Engineering. 2012; 29(6): 1015-20.
[25]	Huang NE, Shen Z, Long SR, Wu MC, Shih HH, Zheng Q, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proceedings Mathematical Physical & Engineering Sciences. 1998; 454(1971): 903-95.
[26]	Hu H, Jing K, Guan L, editors. Instantaneous frequency estimation based on empirical mode decomposition2008.
[27]	Rice WR. A Consensus Combined P-Value Test and the Family-Wide Significance of Component Tests. Biometrics. 1990; 46(2): 303-8.
[28]	Ian, White. Sample Size Calculations in Clinical Research. Journal of the Royal Statistical Society. 2008.
[29]	McGivney DF, Pierre E, Ma D, Jiang Y, Saybasili H, Gulani V, et al. SVD Compression for Magnetic Resonance Fingerprinting in the Time Domain. IEEE Transactions on Medical Imaging. 2014; 33(12): 2311-22.
[30]	Pretorius E, Cronje ML, Strydom O, editors. Development of a pediatric cardiac computer aided auscultation decision support system. International Conference of the IEEE Engineering in Medicine & Biology; 2010.