Heart murmur classification with feature selection

Kumar, Deepak; Carvalho, Paulo; Antunes, M.; Paiva, Rui Pedro; Henriques, J.

doi:10.1109/iembs.2010.5625940

Cited by 34 publications

(13 citation statements)

References 10 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The differences make difficulties in comparative evaluation. However, it is worth noting that in some of the studies, HOC features are combined with other types of features [2,14,15]. Moreover, the features are obtained from different representations of the signals such as DFT, DWT and WVD.…”

Section: Discussionmentioning

confidence: 99%

“…In previous studies on heart sounds, HOC were utilized to provide visualization facilities for interpreting heart sounds by clinicians [6][7][8][9][10][11][12]. Some studies were also reported on using HOC as features extracted for heart sound classification [2,[12][13][14][15]. However, this paper employs HOC to define information measures for basis selection.…”

mentioning

confidence: 90%

See 1 more Smart Citation

Cumulant-based trapezoidal basis selection for heart sound classification

Safara

2015

Med Biol Eng Comput

View full text Add to dashboard Cite

Past decades witnessed the expansion of linear signal processing methods in numerous biomedical applications. However, the nonlinear behavior of biomedical signals revived the interest in nonlinear signal processing methods such as higher-order statistics, in particular higher-order cumulants (HOC). In this paper, HOC are utilized toward heart sound classification. Heart sounds are presented by wavelet packet decomposition trees. Information measures are then defined based on HOC of wavelet packet coefficients, and three basis selection methods are proposed to prune the trees and preserve the most informative nodes for feature extraction. In addition, an approach is introduced to reduce the dimensionality of the search space from the whole wavelet packet tree to a trapezoidal sub-tree of it. This approach can be recommended for signals with a short frequency range. HOC features are extracted from the coefficients of selected nodes and fed into support vector machine classifier. Experimental data is a set of 59 heart sounds from different categories: normal heart sounds, mitral regurgitation, aortic stenosis, and aortic regurgitation. The promising results achieved indicate the capabilities of HOC of wavelet packet coefficients to capture nonlinear characteristics of the heart sounds to be used for basis selection.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 90%

Cumulant-based trapezoidal basis selection for heart sound classification

Safara

2015

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…The highest eigenvalues are associated with the most relevant structures of the signal. In contrast, the lowest eigenvalues are usually associated with very small variations and noise [7]. Using the vector, the entropy gradient is given by:…”

Section: Entropy Gradientmentioning

confidence: 99%

Exploratory Study of the Cardiac Dynamic Trajectory in the Embedding Space

Oliveira

Cardoso

Coimbra

2016

2016 Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

In this paper, the topological and dynamical properties of the heart sounds are assessed. The signal is preprocessed and projected into an embedding subspace, which is more suitable to detect the irregularities and the unstable trajectories registered during the cardiac murmurs than the original heart sound signal.We present a method for heart murmur classification divided into five major steps: a) signal is divided into heart beats; b) entropy gradient envelogram is computed from the pre-processed signal; c) the orbital trajectories are reconstructed using the embedding theory; d) n orbits in the embedding subspace are extracted (per heart beat); e) the median of the n orbits is used as an input to K-Nearest Neighbors (KNN) classifier.The experimental results achieved are in agreement with the current state of art for heart murmur classification. IntroductionHeart sound auscultation using a traditional stethoscope is the simplest, fastest and cheapest method for heart examination. Although the importance of the traditional auscultation methods has decreased due to its inherent restrictions. The phonocardiogram (PCG) has preserved its importance in pediatric cardiology, cardiology, and internal diseases, evaluating congenital cardiac defects. The phonocardiogram is divided into heart cycle (S11) components such as: S1 (first heart sound) and S2 (second heart sound) [1]. These establish the boundaries of the other two fundamental components of a heart cycle: the systole (S21), and the diastole (S12). The S1 and S2 are generated by the opening and closing of the heart valves, in pathogenic situations additional sounds such as S3, S4 or murmurs are listened [1]. Heart murmurs are turbulence phenomena characterized by momentum diffusion, high momentum convection, and rapid variation of pressure and velocity both in space and time [1]. The automatic detection of heart murmurs strongly depends on the extraction of an appropriate set of features, which are hopefully capable of splitting the data into two or more categories: normal and different types of abnormal cases.Ahlstrom proposed a set of 207 features composed by Shannon energy, wavelet coefficients, fractal dimensions and recurrence quantification analysis. A subset of 14 features was derived using a Pudil's sequential floating forward selection algorithm. Using a neural network classifier, this subset achieved 86% of accuracy [2]. Delgado-Trejos compared three types of features: spectral, perceptual and fractal features. Using a K-nearest neighbor's classifier they observed that fractal features provide the best accuracy (97, 17%) followed by spectral (95, 28%) and perceptual features (88,7%). This fact it is explained by the presence of long-range (fractal) correlation along with distinct classes of non-linear interactions [3]. The feature set described in our previous work [4] is a combination of time-frequency domain, perceptual and fractal analysis. We also proposed: 1) the dimension correlation curve; 2) the exponential decay of the false nearest...

show abstract

“…They used 3 domains (time domain, frequency domain and statistical domain). They have sensitivity range (86%-100%) [9]. Some research papers suggested new method for feature extraction in presence of murmur; they extracted feature from different features in phonocardiogram (PCG).…”

Section: Introductionmentioning

confidence: 99%

Improving the Recognition of Heart Murmur

Kotb¹,

Elmahdy²,

Mostafa³

et al. 2016

ijacsa

View full text Add to dashboard Cite

Abstract-Diagnosis of congenital cardiac defects is challenging, with some being diagnosed during pregnancy while others are diagnosed after birth or later on during childhood. Prompt diagnosis allows early intervention and best prognosis. Contemporary diagnosis relies upon the history, clinical examination, pulse oximetery, chest X-ray, electrocardiogram (ECG), echocardiography (ECHO), computed tomography (CT) and cardiac catheterization. These diagnostic modalities reliable upon recording electrical activity or sound waves or upon radiation. Yet, congenital heart diseases are still liable to misdiagnosis because of level of operator expertise and other multiple factors. In an attempt to minimize effect of operator expertise this paper built a classification model for heart murmur recognition using Hidden Markov Model (HMM). This paper used Mel Frequency Cepestral coefficient (MFCC) as a feature and 13 MFCC coefficients. The machine learning model built by studying 1069 different heart sounds covering normal heart sounds, ventricular septal defect (VSD), mitral regurgitation (MR), aortic stenosis (AS), aortic regurgitation (AR), patent ductus arteriosus (PDA), pulmonary regurgitation (PR), and pulmonary stenosis (PS). MFCC feature used to extract feature matrix for each type of heart sounds after separation according to amplitude threshold. The frequency of normal heart sound (range= 1Hz to 139Hz) was specific without overlap with any of the studied defects (ranged= 156-556Hz). The frequency ranges for each of these defects was typical without overlap according to examined heart area (aortic, pulmonary, tricuspid and mitral area). The overall correct classification rate (CCR) using this model was 96% and sensitivity 98%. This model has great potential for prompt screening and specific defect detection. Effect of cardiac contractility, cardiomegaly or cardiac electrical activity on this novel detection system needs to be verified in future works.

show abstract

Heart murmur classification with feature selection

Cited by 34 publications

References 10 publications

Cumulant-based trapezoidal basis selection for heart sound classification

Cumulant-based trapezoidal basis selection for heart sound classification

Exploratory Study of the Cardiac Dynamic Trajectory in the Embedding Space

Improving the Recognition of Heart Murmur

Contact Info

Product

Resources

About