Utilizing wavelet transform and support vector machine for detection of the paradoxical splitting in the second heart sound

Med Biol Eng Comput. 2010 Feb;48(2):177-84. doi: 10.1007/s11517-009-0548-7. Epub 2009 Nov 19.

Abstract

Paradoxical splitting occurs when pulmonic valve (P2) closes before the aortic valve (A2). This causes second heart sound (S2) to be a single sound during inspiration and split during exhalation. Etiology delay in aortic closure: aortic stenosis, volume overload of left ventricle (LV), conduction defects in LV, and left bundle branch block (LBBB). In this article, a method was proposed in early detection of a reverse in the appearance of A2 and P2 within S2. This method is based on the time-frequency maps obtained with the continuous wavelet transform (CWT), namely, the Meyer wavelet. A number of patients with LBBB and others with fitted pacemakers were studied. The above method is combined with the support vector machine (SVM) and performance of this method is evaluated using classification accuracy (Ca), sensitivity (Se), specificity, positive, and negative predicted values. Results show that it is relatively easy to detect the reverse in A2 and P2 and the Ca and Se is 90.97 and 94.44%, respectively, for the sample of 42 patients whose data were collected from the Cardiology Department at Brighton and Sussex University Hospital in England.

MeSH terms

  • Aortic Valve / physiopathology
  • Bundle-Branch Block / diagnosis
  • Cardiac Pacing, Artificial
  • Heart Murmurs / diagnosis*
  • Humans
  • Phonocardiography / methods
  • Pulmonary Valve / physiopathology
  • Signal Processing, Computer-Assisted*
  • Wavelet Analysis