Table 5. Accuracy performance results of the male patients.

Remark that the accuracy is computed as $\frac{\text{TP}+\text{TN}}{\text{TP}+\text{TN}+\text{FP}+\text{FN}}$. The columns show: the UPDRS score (marked as NaN in the case of healthy patients), the benchmark measures performances, corresponding to the MFCCs, MGDCCs, Jitter(%): frequency perturbation, Shimmer (dB): amplitude perturbation, APQ (%): amplitude perturbation quotient, PPQ (%): pitch perturbation quotient, RAP (%): relative average perturbation, CPP mean: mean of cepstral peak prominence corresponding to the mean of voice quality perturbation and CPP s.d.: variation in the cepstral peak prominence corresponding to variation in voice quality perturbation, as given in [29]. Note that the used classifier is the SVM. A cross-validation has been performed for any of the presented results and, therefore, the provided accuracy are the averaged accuracy scores. Configuration for the cross-validation for the benchmark features and the SVM are given in 7.4.

State-of-the-art Benchmark Male Results (Non-EMD Speech Data Based Approaches)—Accuracy
Healthy Patients
UPDRS	Benchmark (SVM)				Benchmark—not averaged (SVM)				Benchmark—standard (SVM)
	MFCCs	MGDCCs	MFCCs + MGDCCs	MFCCs	MGDCCs	MFCCs + MGDCCs	Jitter	Shimmer	APQ	PPQ	RAP	CPP mean	CPP s.d.
NaN	0.410	0.515	0.519	0.500	0.511	0.558	0.379	0.583	0.264	0.327	0.453	0.463	0.472
NaN	0.643	0.590	0.571	0.519	0.576	0.598	0.379	0.463	0.527	0.274	0.463	0.665	0.655
Sick Patients
UPDRS	Benchmark (SVM)				Benchmark—not averaged (SVM)				Benchmark—standard (SVM)
	MFCCs	MGDCCs	MFCCs + MGDCCs	MFCCs	MGDCCs	MFCCs + MGDCCs	Jitter	Shimmer	APQ	PPQ	RAP	CPP mean	CPP s.d.
0	0.520	0.650	0.611	0.551	0.656	0.678	0.627	0.573	0.647	0.445	0.465	0.653	0.365
0	0.555	0.600	0.619	0.458	0.623	0.674	0.602	0.553	0.453	0.543	0.637	0.455	0.446
0	0.390	0.588	0.690	0.553	0.598	0.593	0.535	0.511	0.453	0.554	0.553	0.437	0.372
0	0.430	0.590	0.699	0.441	0.489	0.563	0.635	0.563	0.477	0.564	0.574	0.463	0.477
0	0.551	0.500	0.652	0.428	0.649	0.693	0.610	0.674	0.342	0.245	0.572	0.425	0.254
1	0.439	0.595	0.702	0.469	0.532	0.564	0.456	0.467	0.578	0.656	0.564	0.564	0.463
1	0.312	0.610	0.712	0.654	0.689	0.709	0.626	0.465	0.553	0.562	0.465	0.463	0.698
1	0.235	0.645	0.705	0.613	0.601	0.731	0.616	0.505	0.676	0.698	0.687	0.556	0.699
1	0.611	0.650	0.675	0.689	0.673	0.678	0.595	0.666	0.699	0.689	0.687	0.685	0.563
2	0.387	0.611	0.718	0.445	0.562	0.699	0.628	0.668	0.668	0.635	0.678	0.675	0.689
2	0.654	0.674	0.731	0.510	0.661	0.722	0.581	0.677	0.678	0.675	0.698	0.698	0.678
3	0.442	0.659	0.750	0.567	0.698	0.719	0.678	0.659	0.665	0.678	0.699	0.688	0.667