Key result
A proposed algorithm using phonocardiography signals and feature extraction methods achieved an overall accuracy of 99.47% for diagnosing valvular heart diseases.
Why the study?
Does the proposed feature extraction and classification algorithm accurately diagnose valvular heart diseases from PCG signals?
Does the proposed feature extraction and classification algorithm accurately diagnose valvular heart diseases from PCG signals?
A novel machine learning algorithm using PCG signals achieved 99.47% accuracy in diagnosing aortic stenosis, mitral stenosis, and mitral regurgitation.
Supports PCG algorithm development for valvular screening; leaves open prospective clinical validation before practice change.
This article presents a novel method for diagnosis of valvular heart disease (VHD) based on phonocardiography (PCG) signals. Application of the pattern classification and feature selection and reduction methods in analysing normal and pathological heart sound was investigated. After signal preprocessing using independent component analysis (ICA), 32 features are extracted. Those include carefully selected linear and nonlinear time domain, wavelet and entropy features. By examining different feature selection and feature reduction methods such as principal component analysis (PCA), genetic algorithms (GA), genetic programming (GP) and generalized discriminant analysis (GDA), the four most informative features are extracted. Furthermore, support vector machines (SVM) and neural network classifiers are compared for diagnosis of pathological heart sounds. Three valvular heart diseases are considered: aortic stenosis (AS), mitral stenosis (MS) and mitral regurgitation (MR). An overall accuracy of 99.47% was achieved by proposed algorithm.
No takes yet. Share an insight, caveat, or question.
Rouhani et al. (2011) studied Valvular heart disease (aortic stenosis, mitral stenosis, mitral regurgitation). Proposed algorithm using PCG signals and feature extraction/classification was evaluated on Overall accuracy for diagnosis of pathological heart sounds. A proposed algorithm using phonocardiography signals and feature extraction methods achieved an overall accuracy of 99.47% for diagnosing valvular heart diseases.