Rouhani M, Abdoli R
Islamic Azad University, Gonabad branch, Gonabad, Iran.
J Med Eng Technol. 2012 Jan;36(1):42-9. doi: 10.3109/03091902.2011.634946. Epub 2011 Dec 10.
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.
本文提出了一种基于心音图（PCG）信号诊断心脏瓣膜病（VHD）的新方法。研究了模式分类以及特征选择和约简方法在分析正常和病理性心音中的应用。使用独立成分分析（ICA）进行信号预处理后，提取了32个特征。这些特征包括精心挑选的线性和非线性时域、小波和熵特征。通过研究不同的特征选择和特征约简方法，如主成分分析（PCA）、遗传算法（GA）、遗传编程（GP）和广义判别分析（GDA），提取了四个信息量最大的特征。此外，还比较了支持向量机（SVM）和神经网络分类器用于病理性心音的诊断。考虑了三种心脏瓣膜病：主动脉瓣狭窄（AS）、二尖瓣狭窄（MS）和二尖瓣反流（MR）。所提出的算法实现了99.47%的总体准确率。
