Effective Dysphonia Detection Using Feature Dimension Reduction and Kernel Density Estimation for Patients with Parkinson’s Disease

• Published in: PloS one Vol. 9; no. 2; p. e88825
• Main Authors: Yang, Shanshan, Zheng, Fang, Luo, Xin, Cai, Suxian, Wu, Yunfeng, Liu, Kaizhi, Wu, Meihong, Chen, Jian, Krishnan, Sridhar
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 20.02.2014; Public Library of Science (PLoS)
• Subjects: Acoustics; Aged; Area Under Curve; Artificial intelligence; Basis functions; Biomedical engineering; Bivariate analysis; Classification; Classifiers; Communication; Diagnostic systems; Discriminant Analysis; Disease detection; Dysphonia - diagnosis; Dysphonia - etiology; Engineering; Female; Fourier transforms; Humans; Information science; Kernel functions; Kernels; Male; Measurement methods; Medical research; Medicine; Middle Aged; Movement disorders; Neural networks; Neurodegenerative diseases; Otology; Parkinson Disease - complications; Parkinson Disease - pathology; Parkinson's disease; Patients; Pattern analysis; Pattern classification; Phonation - physiology; Principal Component Analysis; Principal components analysis; Radial basis function; Reduction; ROC Curve; Science; Sensitivity and Specificity; Signal processing; Social and Behavioral Sciences; Statistical analysis; Statistical methods; Studies; Support Vector Machine; Support vector machines; Telemedicine; Voice control
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0088825

Detection of dysphonia is useful for monitoring the progression of phonatory impairment for patients with Parkinson's disease (PD), and also helps assess the disease severity. This paper describes the statistical pattern analysis methods to study different vocal measurements of sustained phonations. The feature dimension reduction procedure was implemented by using the sequential forward selection (SFS) and kernel principal component analysis (KPCA) methods. Four selected vocal measures were projected by the KPCA onto the bivariate feature space, in which the class-conditional feature densities can be approximated with the nonparametric kernel density estimation technique. In the vocal pattern classification experiments, Fisher's linear discriminant analysis (FLDA) was applied to perform the linear classification of voice records for healthy control subjects and PD patients, and the maximum a posteriori (MAP) decision rule and support vector machine (SVM) with radial basis function kernels were employed for the nonlinear classification tasks. Based on the KPCA-mapped feature densities, the MAP classifier successfully distinguished 91.8% voice records, with a sensitivity rate of 0.986, a specificity rate of 0.708, and an area value of 0.94 under the receiver operating characteristic (ROC) curve. The diagnostic performance provided by the MAP classifier was superior to those of the FLDA and SVM classifiers. In addition, the classification results indicated that gender is insensitive to dysphonia detection, and the sustained phonations of PD patients with minimal functional disability are more difficult to be correctly identified.