Table 4.

List of comparable studies.

Data seta	Classifier	Feature	Performance	Reference
CFSb (donator)	SVMc	MFCCd and TQWTe	Accuracy: 0.8600	[48]
UCIf	GBg	BLAh and spectrum	Accuracy: 0.9388	[44]
UCI	KNNi	TQWT	Accuracy: 0.9800	[55]
UCI	ANNj	BLA	Accuracy: 0.9921	[40]
UCI	SVM	BLA, MFCC, WTk, and TQWT	Accuracy: 0.9160	[42]
UCI	ANN	MFCC	Accuracy: 0.9674	[61]
UCI	NBl	BLA	Accuracy: 0.7897	[64]
UCI	SVM	BLA, MFCC, TQWT, and WT	Accuracy: 0.9470	[68]
UCI	SVM	BLA, MFCC, WT, and TQWT	Accuracy: 0.9350	[99]
UCI	SVM	BLA, MFCC, and TQWT	Accuracy: 0.8660	[119]
UCI	KNN	TQWT	Accuracy: 0.9890	[121]
UCI	RFm	BLA and MFCC	Accuracy: 0.8884	[122]
UCI	ANN	BLA, MFCC, and TQWT	Accuracy: 0.9200	[124]
UCI	SVM	BLA, MFCC, TQWT, and WT	Accuracy: 0.9621	[126]
UCI	ANN	BLA, MFCC, and TQWT	Accuracy: 0.9974	[127]
UCI	SVM	BLA	Accuracy: 0.6701	[53]
UCI	RF	BLA and MFCC	Accuracy: 0.9433	[57]
UCI	ANN	BLA	Accuracy: 0.9903	[60]
UCI	ANN	BLA	Accuracy: 0.8647	[72]
UCI	SVM	BLA and MFCC	Accuracy: 0.8750	[100]

^aItalicized data sets represent Parkinson disease data set 2 containing data on patients with Parkinson disease (n=20) and HC (n=20); all other data sets correspond to Parkinson disease data set 1 containing data on patients with Parkinson disease (n=188) and HC (n=64).

^bCFS: collected for study.

^cSVM: support vector machine.

^dMFCC: Mel-frequency cepstral coefficients.

^eTQWT: tunable Q-factor wavelet transform.

^fUCI: University of California, Irvine.

^gGB: gradient boosting.

^hBLA: baseline acoustic.

ⁱKNN: K-nearest neighbor.

^jANN: artificial neural network.

^kWT: wavelet.

^lNB: naïve Bayes.

^mRF: random forest.