We present a novel, low complexity method for the detection of the first and second of heart sounds (S1 and S2, respectively) and the periods of systole and diastole without using an electrocardiogram reference. The algorithm uses a technique called empirical mode decomposition to produce intensity envelopes of the main heart sounds in the time domain. The performance of the algorithm was evaluated using 14,000 cardiac periods from 100 normal and abnormal digital phonocardiographic recordings. The sensitivity of the detection method was 88.3% for both S1 and S2, and the precision (positive predictive value) was 95.8% for both S1 and S2.
RangayyanRMLehnerRJ. Phonocardiogram signal analysis: a review. Crit Rev Biomed Eng1987; 15(3): 211–236.
2.
SegaierMELiljaOLukkarinenS. Computer-based detection and analysis of heart sound murmur. Ann Biomed Eng2005; 33(7): 937–942.
3.
CarvalhoPGilPHenriquesJ. Low complexity algorithm for heart sound segmentation using the variance fractal dimension. In: IEEE international workshop on intelligent signal processing, University of Algarve, Portugal1–3 September 2005, pp.194–199. IEEE.
4.
HebdenJETorryIN. Neural network and conventional classifiers to distinguish between first and second heart sound. In: IEEE colloquium on artificial intelligence methods for biomedical data processing, Institution of Electrical Engineers London, UK, 26 April 1996, pp.1–6. IEEE.
5.
StasisACLoukisENPavlopoulosSA. Using decision tree algorithm as a basis for a heart sound diagnosis decision support system. In: 4th international IEEE EMBS special topic conference on information technology applications in biomedicine, The Institute of Electrical and Electronics Engineers, Birmingham, UK24–26 April 2003, pp.354–357. IEEE.
6.
LiangHLukkarinenSHartimoI. Heart sound segmentation algorithm based on heart sound envelogram. In: Conference on computers in cardiology, The institute of electrical and electronics engineers, Lund, Sweden, 7–10 September 1997, pp.105–108. IEEE.
7.
LiangHLukkarinenSHartimoI. A boundary modification method for heart sound segmentation algorithm. In: Conference on computers in cardiology, The Institute of Electrical and Electronics Engineers, Cleveland, OH, 13–16 September 1998, pp.593–595. IEEE.
8.
KumarDCarvalhoPGilP. A new algorithm for detection of S1 and S2 heart sounds. In: Proceedings of IEEE international conference on acoustics, speech and signal processing, vol. 2, The Institute of Electrical and Electronics Engineers, Toulouse, France, 14–19 May 2006, pp.1180–1183. IEEE.
9.
RehmanNMandicDP. Empirical mode decomposition for trivariate signals. IEEE Trans Signal Process2010; 58(3): 1059–1068.
10.
LeePLShangLZWuYT. Single-trial analysis of cortical oscillatory activities during voluntary movements using empirical mode decomposition (EMD)-based spatiotemporal approach. Ann Biomed Eng2009; 37(8): 1683–1700.
11.
ZhangYGaoYWangL. The removal of wall components in Doppler ultrasound signals by using the empirical mode decomposition algorithm. IEEE Trans Biomed Eng2007; 54(9): 1631–1642.
12.
SalisburyJISunY. Assessment of chaotic parameters in nonstationary electrocardiograms by use of empirical mode decomposition. Ann Biomed Eng2004; 32(10): 1348–1354.
NorgardGVik-MoH. Effects of respiration on right ventricular size and function: an echocardiography study. Pediatr Cardiol1992; 13(3): 136–140.
15.
ZhendongY. Effects of age and respiration on right ventricular diastolic filling pattern in normal children. Pediatr Cardiol1998; 19(3): 218–220.
16.
LendrumBLMondkarAMBrian HarrisJ. Respiratory variation in echocardiographic dimensions of left and right ventricles in normal children. Pediatr Cardiol1979; 1: 39–45.
17.
NandiPSPigottVMSpodickDH. Sequential cardiac responses during the respiratory cycle: patterns of change in systolic intervals. Chest1973; 63(3): 380–385.
18.
OmranSTayelM. A heart sound segmentation and feature extraction algorithm using wavelets. In: 1st international symposium on control, communications and signal processing, The institute of electrical and electronics engineers, Hammamet, Tunisia, 21-24 March 2004, pp.235–238. IEEE.
TsengYLKoPYJawFS. Detection of the third and fourth heart sounds using Hilbert-Huang transform. Biomed Eng Online2012; 11: 11–18.
21.
HuangNEShenZLongSR. The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. P Roy Soc A: Math Phy1998; 454(1971): 903–995.
22.
MijovicBDe VosMGligorijevicI. Source separation from single-channel recordings by combining empirical-mode decomposition and independent component analysis. IEEE Trans Biomed Eng2010; 57(9): 2188–2196.
23.
HuangNEShenSS (ed.). Hilbert-Huang transform and its applications: interdisciplinary mathematical sciences. Singapore: World Scientific, 1999.
24.
AriSSahaG. Classification of heart sounds using empirical mode decomposition based features. Int J Med Eng Inform2008; 1(1): 91–108.
25.
GrochMWDomnanovichJRErwinWD. A new heart-sounds gating device for medical imaging. IEEE Trans Biomed Eng1992; 39(3): 307–310.
26.
ReedTRReedNEFritzsonP. Heart sound analysis for symptom detection and computer-aided diagnosis. Simul Model Pract Th2004; 12(2): 129–146.
27.
JiangZChoiS. Comparison of envelope extraction algorithms for cardiac sound signal segmentation. Expert Syst Appl2008; 34(2): 1056–1069.
28.
VepaJTolayPJainA. Segmentation of heart sounds using simplicity features and timing information. In: IEEE international conference on acoustics, speech and signal processing, The Institute of Electrical and Electronics Engineers, Las Vegas, NV, 31 March–4 April 2008, pp.469–472. IEEE.
MarcusGVesseyJJordanMV. Relationship between accurate auscultation of a clinically useful third heart sound and level of experience. Arch Intern Med2006; 166(6): 617–622.
31.
RoosMToggweilerSJamshidiP. Noninvasive detection of left ventricular systolic dysfunction by acoustic cardiography in cardiac failure patients. J Card Fail2008; 14(4): 310–319.
