Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods

<div>Classification results of the generalized logistic regression analysis (GLRA), support vector machine (SVM), Bagging ensemble, and input with the MKLD and ICPR selected features, respectively. GLRA-MKLD: sensitivity: 0.9116; specificity: 0.5833; MCC: 0.5232; GLRA-ICPR: sensitivity: 0.932; specificity: 0.5833; MCC: 0.5604; SVM-MKLD: sensitivity: 0.9048; specificity: 0.8333; MCC: 0.7105; SVM-ICPR: sensitivity: 0.9252; specificity: 0.8542; MCC: 0.7592; Bagging-MKLD: sensitivity: 0.9592; specificity: 0.6875; MCC: 0.6964; Bagging-ICPR: sensitivity: 0.9796; specificity: 0.6875; MCC: 0.6977.</div>

Computational and Mathematical Methods in Medicine

fig3

Figure 3

Figure 3: Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods 

Figure 3 | Dysphonic Voice Pattern Analysis of Patients in Parkinson’s Disease Using Minimum Interclass Probability Risk Feature Selection and Bagging Ensemble Learning Methods 