Changes in Phonation and Their Relations with Progress of Parkinson’s Disease

applied sciences Article Changes in Phonation and Their Relations with Progress of Parkinson’s Disease Zoltan Galaz 1, Jiri Mekyska 1, Vojtech Zvoncak 1, Jan Mucha 1, Tomas Kiska 1, Zdenek Smekal 1, Ilona Eliasova 2,3, Martina Mrackova 2,3, Milena Kostalova 3,4, Irena Rektorova 2,3,*, Marcos Faundez-Zanuy 5, Jesus B. Alonso-Hernandez 6 and Pedro Gomez-Vilda 7 1Department of Telecommunications, Brno University of Technology, Technicka 10, 616 00 Brno, Czech Republic; [email protected].cz (Z.G.); [email protected].cz (J.M.); [email protected] (V.Z.); [email protected].cz (J.M.); [email protected].cz (T.K.); [email protected].cz (Z.S.) 2First Department of Neurology, St. Anne’s University Hospital, Pekarska 53, 656 91 Brno, Czech Republic; [email protected] (I.E.); [email protected] (M.M.) 3Applied Neuroscience Research Group, Central European Institute of Technology, Masaryk University, Kamenice 5, 625 00 Brno, Czech Republic; [email protected] 4Department of Neurology, Faculty Hospital and Masaryk University, Jihlavska 20, 639 00 Brno, Czech Republic 5Escola Superior Politecnica, Tecnocampus, Avda. Ernest Lluch 32, 083 02 Mataro, Barcelona, Spain; [email protected] 6Institute for Technological Development and Innovation in Communications (IDeTIC), University of Las Palmas de Gran Canaria, 35001 Las Palmas de Gran Canaria, Spain; [email protected] 7Neuromorphic Processing Laboratory (NeuVox Lab), Center for Biomedical Technology, Universidad Politecnica de Madrid, Campus de Montegancedo, s/n, Pozuelo de Alarcon, 28223 Madrid, Spain; [email protected] *Correspondence: irena.rektor[email protected]; Tel.: +420-543-182-639 Received: 17 October 2018; Accepted: 19 November 2018; Published: 22 November 2018   Abstract: Hypokinetic dysarthria, which is associated with Parkinson’s disease (PD), affects several speech dimensions, including phonation. Although the scientific community has dealt with a quantitative analysis of phonation in PD patients, a complex research revealing probable relations between phonatory features and progress of PD is missing. Therefore, the aim of this study is to explore these relations and model them mathematically to be able to estimate progress of PD during a two-year follow-up. We enrolled 51 PD patients who were assessed by three commonly used clinical scales. In addition, we quantified eight possible phonatory disorders in five vowels. To identify the relationship between baseline phonatory features and changes in clinical scores, we performed a partial correlation analysis. Finally, we trained XGBoost models to predict the changes in clinical scores during a two-year follow-up. For two years, the patients’ voices became more aperiodic with increased microperturbations of frequency and amplitude. Next, the XGBoost models were able to predict changes in clinical scores with an error in range 11–26%. Although we identified some significant correlations between changes in phonatory features and clinical scores, they are less interpretable. This study suggests that it is possible to predict the progress of PD based on the acoustic analysis of phonation. Moreover, it recommends utilizing the sustained vowel /i/ instead of /a/. Keywords: phonation; acoustic analysis; follow-up study; hypokinetic dysarthria; Parkinson’s disease Appl. Sci. 2018,8, 2339; doi:10.3390/app8122339 www.mdpi.com/journal/applsci Appl. Sci. 2018,8, 2339 2 of 18 1. Introduction Parkinson’s disease (PD) is a frequent neurodegenerative disorder that is associated with a substantial reduction of dopaminergic neurons especially in substancia nigra pars compacta [ 1 ]. The primary motor symptoms of PD comprise tremor at rest, muscular rigidity, bradykinesia, and postural instability [ 1 ]. Patients with PD also develop a variety of non-motor symptoms [ 2 ] such as sleep disturbances, depression, cognitive impairment, etc. To diagnose, rate and monitor motor and non-motor symptoms of PD, various clinical rating scales such as Unified Parkinson’s Disease Rating Scale (UPDRS) [ 3 ], Freezing Of Gait Questionnaire (FOG-Q) [ 4 ], or Addenbrooke’s Cognitive Examination-Revised (ACE–R) [ 5 ] have been developed. Nevertheless, reliability of the assessment is often reduced by inter-rater variability [6]. Up to 90% [ 7 ] of patients with PD develop a multi-dimensional speech disorder named hypokinetic dysarthria (HD) [ 8 ], which is manifested in phonation, articulation, and prosody [ 9 – 11 ]. In the area of phonation, insufficient breath support, reduction in phonation time, increased acoustic noise, instability of articulatory organs, microperturbations of frequency/amplitude, and harsh breathy voice quality has been observed [ 9 , 12 ]. HD leads to serious complications in daily communication of patients with PD [13]. Generally, HD was found to be more severe in the advanced stages of PD [14]. As reported by the recent studies, acoustic analysis of HD can provide clinicians with non-invasive and reliable methodology of PD diagnosis, assessment and monitoring [ 9 , 15 ]. Moreover, this methodology has also been used to monitor the efficiency of PD treatment [ 10 , 16 – 18 ]. In the field of acoustic analysis of PD phonation, the authors mostly focused on the sustained vowel /a/ [ 9 ]. Conventional phonatory features such as jitter, shimmer, harmonic-to-noise ratio, degree of unvoiced segments, and formant-based parameters extracted from this vowel have been widely used to diagnose PD [ 12 , 19 – 23 ]. Although Hazan et al. [ 24 ] employed analysis of sustained phonation for diagnosis of PD even in its early stage, based on the recent review [ 9 ], most of the researchers find relevant applications of the phonatory analysis especially in moderate or severe stages of this disorder. For example, the analysis of sustained phonation has been utilized during PD severity assessment. In 2010, Tsanas et al. [ 15 ] enrolled 42 PD patients and parameterized their sustained phonation of vowel /a/ by a set of conventional features that were consequently mapped to UPDRS, part III (motor examination) and the total score of this scale. Using classification and regression trees, they estimated the UPDRSIII score with MAE (mean absolute error) equal to 5.95. The total UPDRS score was estimated with MAE = 7.52. A parametric version of this dataset has been made available for research purposes and other research teams further decreased the estimation error [ 25 – 27 ]. Another work that deals with the automatic clinical scores estimation was published by Mekyska et al. [ 21 ]. In this study, they acquired sustained phonation of vowels /a/, /e/, /i/, /o/, /u/ in 84 PD patients. Modeling conventional and advanced features by random forests provided the estimation of UPDRSIII with MAE = 5.70. In addition, the authors estimated several other clinical scores such as UPDRS, part IV (complications of therapy) with MAE =1.30 or Beck depression inventory (BDI) with MAE =3.12. Even though HD is one of the most problematic aspects of PD, the number of longitudinal studies investigating the evolution of HD in PD over time (based on the acoustic analysis) is very limited [ 28 – 31 ]. If we focus specifically on longitudinal monitoring of sustained phonation, then, in fact, we can identify only one study, which is published by Skodda et al. [ 31 ]. In this work, the authors repeatedly (with average time interval 32.50 months) acquired sustained vowel /a/ in 32 female and 48 male PD patients (age in session 1: 66.28 ± 8.11 years; PD duration in session 1: 6.10 ± 4.63 years; UPDRSIII in session 1: 20.16 ±10.96; UPDRS III in session 2: 19.58 ±8.29). The voice was quantified by jitter, shimmer, noise-to-harmonic ratio, and mean fundamental frequency. Based on the paired t -test, the authors identified significant changes in shimmer and noise-to-harmonic ratio. In both cases, the values of these parameters increased. Another interesting finding is that, although some phonatory features significantly changed, UPDRS III was held widely stable over time. The authors provide two possible explanations: (1) voice impairment could be the result of an escalation of axial dysfunction too subtle to be mirrored by UPDRSIII; (2) alterations of speech parameters could be Appl. Sci. 2018,8, 2339 3 of 18 completely independent of motor performance that may be based upon non-dopaminergic mechanisms. Inconsistencies in terms of the L-dopa effect on HD are further discussed in Brabenec et al. [9]. To sum it up, although the scientific community frequently addresses phonation in association with HD (especially when diagnosing or assessing PD), to the best of our knowledge, there is only one study that focuses on HD phonatory disorders from a longitudinal perspective. Moreover, the work deals with the analysis of phonation just partially, it considers only the sustained vowel /a/, and it does not explore a possibility of PD progress prediction based on a combination of acoustic analysis and machine learning. Therefore, in the frame of our two-year follow-up study, we are going much further with the following aims: 1. to identify phonatory acoustic features at baseline that are significantly correlated with changes in various clinical rating scales, 2. to investigate relationship between changes in the phonatory acoustic features and the clinical rating scales after the two-year follow-up, 3. to establish mathematical models that will estimate the change in clinical rating scales based on the change in acoustic measures, 4. to compare results based on five vowels: /a/, /e/, /i/, /o/, /u/. The rest of this article is organized as follows: Section 2describes a dataset of PD patients as well as methodology in terms of acoustic analysis, statistical analysis and machine learning. Results are reported in Section 3and consequently discussed in Section 5. Finally, conclusions are given in Section 4. 2. Materials and Methods 2.1. Dataset In this work, we enrolled 51 patients with idiopathic PD. All of them are Czech native speakers (17 females and 34 males; age: 65.47 ± 7.46 years; PD duration: 7.61 ± 4.01 years; mean LED (L-dopa equivalent daily dose) [ 32 ]: 1033.67 ± 567.96 mg/day) at the First Department of Neurology, St. Anne’s University Hospital in Brno, Czech Republic. After two years, the patients were re-examined (age: 67.61 ± 7.38 years; PD duration: 9.57 ± 4.50 years; mean LED: 1115.11 ± 484.38 mg/day). All patients signed an informed consent form that has been approved (including the study) in 14 March 2016 by the Research Ethics Committee of Masaryk University (ref. no.: EKV-2016-004, project title: Effects of non-invasive brain stimulation on hypokinetic dysarthria, micrographia, and brain plasticity in patients with Parkinson’s disease, investigator: Prof. MD. Irena Rektorova, PhD.). None of the patients had a disease affecting the central nervous system other than PD. All patients were examined on their regular dopaminergic medication approximately 1 h after the L-dopa [ 32 ] dose. The following rating scales were used to evaluate the clinical symptoms of PD: UPDRSIII and UPDRSIV [ 3 ], FOG-Q [ 4 ], REM sleep behavior disorder screening questionnaire (RBDSQ) [ 33 ], and ACE-R [ 5 ]. The full clinical characteristics of the dataset, ie., mean ± sd values for the clinical rating scales in session 1, session 2, and session ∆ ( session 2 −session 1 ) can be seen in Table 1. Moreover, to identify statistically significant differences, the table reports p-values of the Wilcoxon signed-rank test between the data acquired in session 1 (baseline examination) and session 2 (two-year follow-up examination) too. The clinical data from the ∆ session were also used to generate descriptive visualizations (i.e., histograms, regression and residual plots) for the change in selected clinical rating scales, more specifically: LED, UPDRS III, UPDRSIV, FOG-Q, RBDSQ, ACE-R, see Figure 1. With this approach, it is possible to assess the improvement and/or decline in motor and non-motor deficits associated with PD in the horizon of two years as well as a relationship between the change in each of the scales relative to other scales in the selected set. Appl. Sci. 2018,8, 2339 4 of 18 Table 1. Clinical characteristics of the patients. Scale Mean ±sd (s1) Mean ±sd (s2) Mean ±sd (∆)p(Wilcoxon) LED 917.61 ±544.78 1129.92 ±477.50 212.31 ± −67.28 0.188 UPDRSIII 22.49 ±13.47 27.45 ±12.68 4.96 ± −0.79 0.000 UPDRSIV 2.82 ±2.58 3.44 ±2.94 0.62 ±0.36 0.632 FOG-Q 6.57 ±5.40 8.33 ±5.97 1.76 ±0.57 0.000 RBDSQ 3.98 ±3.25 3.78 ±2.28 −0.2 ± −0.98 0.522 ACE-R 87.92 ±7.62 85.89 ±9.48 −2.03 ±1.86 0.000 s1—first session; s2—second session; ∆ —delta session ( session 2 −session 1 ); p(Wilcoxon) — p-value for Wilcoxon signed-rank test (paired samples); LED—L-dopa equivalent daily dose (mg/day) [ 32 ]; UPDRSIII—Unified Parkinson’s Disease Rating Scale, partIII: evaluation of motor function [ 3 ], UPDRSIV—Unified Parkinson’s Disease Rating Scale, part IV: evaluation of complications of therapy [ 3 ]; FOG-Q—Freezing of gait questionnaire [ 4 ]; RBDSQ—The REM sleep behavior disorder screening questionnaire [33]; ACE-R—Addenbrooke’s Cognitive Examination-Revised [5].                                                Figure 1. Descriptive statistical graphs of clinical characteristics of the PD patient dataset: on the main diagonal, histograms are visualized. Next, the upper triangular part of the graph-grid shows scatter plots with the fitted lines of linear regression models. Finally, the lower triangular part of the graph-grid is used to display residuals for the models shown in the upper grid. Color notation: the blue color represents data for session 1, and the green color represents data for session 2. Appl. Sci. 2018,8, 2339 5 of 18 2.2. Vocal Tasks To quantify the deterioration of phonation in patients with PD, we used a sustained phonation of vowels: /a/, /e/, /i/, /o/, /u/ as a basis for our experiments. The reason behind using all of the five vowels is to employ the analysis with the emphasis on quantifying all positions of a tongue during phonation. For more information, see the Hellwag (vowel) triangle [ 34 ]. In our view, using only a sustained phonation of the vowel /a/ is not fully justified as there is very little or no reason to assume that this particular position of the tongue can provide more information about phonatory disorders. In fact, as shown by previous studies, the analysis of other vowels is important for a more robust description of HD [19–21,23,24,35–37]. Sustained phonation of a vowel is a standard measure used to assess quality of phonation [ 9 ]. During this particular vocal task, a speaker is asked to sustain phonation of a vowel, attempting to maintain steady frequency and amplitude at a comfortable level [ 38 ]. The advantage of this task in comparison with other commonly used vocal tasks is its independence of articulatory and other linguistic confounds [ 38 ]. Moreover, it is also present in most of the databases and therefore the experiments proposed in our work are comparable with other commonly used databases [39,40]. The sustained phonation task used in this study is a part of a speech acquisition protocol derived from the standardized 3F Dysarthria Profile [ 41 ]. During the data acquisition, a large capsule cardioid microphone M-AUDIO Nova (Cumberland, RI, United States) mounted to a boom arm RODE PSA1 (Silverwater, Australia) and positioned at a distance of approximately 20cm from the patient’s mouth was used for the recording. Consequently, the signals were digitized by audio interface M-AUDIO Fast Track Pro (Cumberland, RI, United States) with the sampling frequency of 48kHz (16-bit resolution) and checked by a trained acoustic engineer without having seen the patient’s clinical data. Finally, the signals were parameterized using Praat [ 42 ] software as well as a set of MATLAB (MATLAB 9.4, MathWorks, Natick, MA, United States) parametrization functions [ 43 ] developed at the Brno University of Technology. 2.3. Acoustic Features To describe a variety of phonatory disorders associated with HD, we quantified the following: (a) microperturbations in frequency of voice using period perturbation quotient (PPQ); (b) microperturbations in intensity of voice using amplitude perturbation quotient (APQ); (c) irregular pitch fluctuations using coefficient of variation of fundamental frequency (F0 (CV)); (d) irregular amplitude fluctuations using coefficient of variation of Teager–Kaiser operator (TKEO (CV)); (e) tremor of articulatory organs (such as jaw, tongue and lips), coefficient of variation of 1st formant (F1 (CV)), coefficient of variation of 2nd formant (F2 (CV)), coefficient of variation of 3rd formant (F3 (CV)); (f) increased acoustic noise using median of harmonic-to-noise ratio (HNR (Q2)), median of energy ratio (ER (Q2), energy ratio of bands 2000–4000Hz and 70–900Hz)), median of glottal-to-noise excitation ratio (GNE (Q2)), median of normalized noise energy (NNE (Q2)); (g) irregular acoustic noise fluctuations using standard deviation of harmonic-to-noise ratio (HNR (SD)), coefficient of variation of energy ratio (ER (CV)), standard deviation of glottal-to-noise excitation ratio (GNE (SD)), standard deviation of normalized noise energy (NNE (SD)); and (h) aperiodicity of voice using fraction of locally unvoiced frames (FLUF). All of these features are standard and clinically interpretable dysphonic measures and were selected based on a recommendation given in our recent review on acoustic analysis of voice/speech signals in patients suffering from HD [ 9 ]. For more information about the voice/speech parametrization, see [43]. 2.4. Statistical Analysis Before describing the analytical setup applied in this work, it is important to mention that the dataset did not contain any missing values, and therefore all data samples were used. Furthermore, even though we used six clinical rating scales when describing the dataset (see Section 2.1), only four Appl. Sci. 2018,8, 2339 6 of 18 of these scales were used for the analysis, specifically: UPDRSIII, UPDRS IV, RBDSQ, and FOG-Q. The reason is that previous studies have already shown that non-motor manifestations of PD are not linked with the phonatory aspects of HD, but rather with the impairments of prosody and articulation [ 44 ] that are commonly being quantified using a sentence reading task, free speech (monologue), etc. Since this study is focused on the phonatory aspects of HD, clinical rating scales describing only motor symptoms of PD were used. To reveal and assess the strength of a relationship between the computed acoustic features and patients’ clinical data (UPDRSIII, UPDRSIV, RBDSQ, and FOG-Q), Spearman’s correlation coefficient was computed (the statistical assumptions for Spearman’s correlation coefficient were satisfied as: (a) the acoustic features as well as the the clinical data are both variables that are measured on at least an ordinal scale, and (b) there is a monotonic relationship between the two variables). Since age, gender, and probably L-dopa, are manifested in a voice of PD patients [ 9 ], for the purpose of this work, we employed partial Spearman’s correlation controlling for the effect of the following confounding factors (also known as covariates): patients’ age, gender [ 29 , 45 ], and dopaminergic medication [ 32 , 46 ]. The significance level of correlation was set to 0.05. More specifically, two correlation scenarios were considered: (a) correlation between the acoustic features at the baseline and the change in values of the selected clinical rating scales, and (b) correlation between the change in the acoustic features and the change in the values of the selected clinical rating scales. With this approach, we aimed at identifying those acoustic features that are significantly correlated with the specific motor and non-motor symptoms assessed by the selected clinical rating scales in both scenarios. Next, to evaluate the power of the acoustic features at the baseline to predict the change of the patients’ clinical data in the horizon of two years, we used the acoustic features computed for the recordings acquired in session 1 (baseline examination) and built mathematical models predicting the change in the selected clinical rating scales ( ∆ ). For this purpose, we employed Gradient Boosted Trees (more specifically, the famous XGBoost algorithm [ 47 ]) in a supervised learning setup: 10-fold cross-validation with 20 repetitions [ 48 ]. The XGBoost algorithm belongs to the state-of-the-art in machine learning, which is supported by the fact that it has been recently used to win competitions on Kaggle. It works well even on small datasets (where it outperforms deep learning approaches), it is robust to outliers and it is able to model complex interdependencies. For these reasons, it has been used by many researchers in various biomedical fields, e.g., [49–51], etc. The performance of the models (precision of the predictions) was evaluated by MAE and estimation error rate (EER). These measures are defined as: MAE =1 n n ∑ i=1 |yi−ˆ yi|, EER =1 n·r n ∑ i=1 |yi−ˆ yi| · 100 [%], where yi stands for the true label of i -th observation, ˆ yi represents the predicted label of the i -th observation, n denotes the number of observations, and finally r stands for the range of values in the predicted clinical rating scale (not the range that can be theoretically reached, but the actual range of the values in the dataset). As can be seen, EER therefore describes a percentage of error predictions with respect to statistical properties of the dataset, which is particularly useful for easy interpretation of the results. 3. Results The values of 16 acoustic features extracted from both sessions, as well as values of their differences (session 2 − session 1), are reported in Table 2. Based on the Wilcoxon signed-rank test, we can observe that none of the features extracted from vowel /a/ significantly changed after two years. Regarding vowel /e/, we identified significantly increased microperturbations in intensity of voice and also Appl. Sci. 2018,8, 2339 7 of 18 increased aperiodicity. The same significant changes were identified in vowel /i/ and /u/. In the case of vowel /u/, in addition, we monitored the increase of microperturbations in frequency of voice. The repeated acquisition of vowel /o/ was associated with increased aperiodicity and more dominant microperturbations in frequency of voice. Table 2. Statistical description of acoustic features for all vocal tasks. Feature Mean ±sd (s1) Mean ±sd (s2) Mean ±sd (∆)p(Wilcoxon) vowel /a/ PPQ 1.31 ±1.28 1.89 ±2.52 0.58 ±1.24 0.069 APQ 10.69 ±4.23 12.81 ±6.66 2.12 ±2.42 0.063 FLUF 3.87 ±5.28 4.77 ±5.61 0.90 ±0.32 0.386 HNR (Q2) 13.35 ±2.90 12.81 ±3.73 −0.54 ±0.83 0.390 HNR (SD) 4.17 ±0.86 4.18 ±0.89 0.02 ±0.03 0.928 F1 (CV) 0.15 ±0.06 0.18 ±0.10 0.02 ±0.04 0.180 F2 (CV) 0.22 ±0.15 0.23 ±0.15 0.00 ±0.00 0.913 F3 (CV) 8.25 ±40.44 4.50 ±21.67 −3.75 ± −18.77 0.575 ER (Q2) 6.98 ±33.97 7.40 ±36.43 0.42 ±2.46 0.954 ER (CV) 0.57 ±0.26 0.57 ±0.30 0.01 ±0.05 0.880 F0 (CV) 0.30 ±0.74 0.36 ±1.15 0.06 ±0.41 0.763 GNE (Q2) −0.46 ±1.85 −0.46 ±1.85 0.00 ± −0.00 0.997 GNE (SD) 0.23 ±0.74 0.30 ±0.97 0.07 ±0.23 0.679 TEO (CV) −0.34 ±1.71 −0.31 ±1.75 0.03 ±0.04 0.931 NNE (Q2) −1.45 ±7.41 −1.33 ±7.08 0.13 ± −0.34 0.932 NNE (SD) 1.80 ±0.76 1.79 ±0.78 −0.01 ±0.02 0.955 vowel /e/ PPQ 1.31 ±1.17 1.80 ±3.06 0.50 ±1.89 0.269 APQ 11.21 ±6.82 15.05 ±9.95 3.84 ±3.13 0.036 FLUF 2.62 ±3.58 5.31 ±6.02 2.69 ±2.44 0.007 HNR (Q2) 14.36 ±3.92 13.75 ±4.40 −0.61 ±0.48 0.394 HNR (SD) 4.19 ±0.96 4.32 ±1.18 0.13 ±0.21 0.533 F1 (CV) 0.62 ±0.23 0.56 ±0.24 −0.05 ±0.01 0.173 F2 (CV) 0.19 ±0.07 0.19 ±0.09 −0.00 ±0.02 0.965 F3 (CV) 12.41 ±86.28 7.06 ±48.94 −5.36 ± −37.34 0.709 ER (Q2) 3.46 ±23.30 3.39 ±22.83 −0.07 ± −0.47 0.989 ER (CV) 0.59 ±0.28 0.61 ±0.37 0.02 ±0.10 0.702 F0 (CV) 0.42 ±1.47 0.19 ±0.50 −0.24 ± −0.97 0.293 GNE (Q2) −0.36 ±1.77 −0.17 ±1.18 0.19 ± −0.59 0.536 GNE (SD) 0.08 ±0.36 0.06 ±0.30 −0.02 ± −0.07 0.726 TEO (CV) −0.07 ±0.50 −0.19 ±1.31 −0.11 ±0.80 0.571 NNE (Q2) −0.19 ±1.35 −0.21 ±1.44 −0.01 ±0.10 0.961 NNE (SD) 1.67 ±0.56 1.83 ±0.61 0.17 ±0.05 0.055 vowel /i/ PPQ 1.26 ±1.68 1.92 ±3.08 0.66 ±1.40 0.196 APQ 10.49 ±5.31 14.83 ±9.65 4.35 ±4.34 0.005 FLUF 2.13 ±3.73 4.60 ±6.89 2.46 ±3.15 0.013 HNR (Q2) 17.16 ±3.38 16.17 ±5.32 −0.98 ±1.95 0.212 HNR (SD) 4.51 ±1.12 4.53 ±1.40 0.02 ±0.28 0.921 F1 (CV) 0.67 ±0.48 0.58 ±0.40 −0.09 ± −0.08 0.170 F2 (CV) 0.14 ±0.07 0.16 ±0.08 0.02 ±0.00 0.088 F3 (CV) 0.09 ±0.21 38.22 ±207.82 38.14 ±207.61 0.205 ER (Q2) 0.09 ±0.08 8.35 ±33.15 8.27 ±33.07 0.087 ER (CV) 0.61 ±0.37 0.56 ±0.44 −0.05 ±0.07 0.490 F0 (CV) 0.36 ±1.39 0.35 ±1.17 −0.01 ± −0.22 0.961 GNE (Q2) −0.30 ±1.49 −0.30 ±1.48 0.01 ± −0.01 0.980 GNE (SD) 0.07 ±0.32 0.12 ±0.40 0.06 ±0.08 0.449 TEO (CV) 0.78 ±0.55 0.36 ±2.47 −0.42 ±2.47 0.238 NNE (Q2) −0.01 ±0.18 −0.20 ±11.53 −0.19 ±1.15 0.228 NNE (SD) 1.44 ±0.55 1.40 ±0.70 −0.05 ±0.15 0.727 Appl. Sci. 2018,8, 2339 8 of 18 Table 2. Cont. Feature Mean ±sd (s1) Mean ±sd (s2) Mean ±sd (∆)p(Wilcoxon) vowel /o/ PPQ 1.14 ±1.06 1.68 ±2.06 0.54 ±0.99 0.047 APQ 11.09 ±4.41 14.16 ±9.94 3.06 ±5.53 0.051 FLUF 2.64 ±4.32 5.63 ±7.24 2.99 ±2.91 0.008 HNR (Q2) 15.49 ±3.30 15.28 ±4.79 −0.22 ±1.49 0.773 HNR (SD) 4.93 ±1.14 4.57 ±1.36 −0.36 ±0.21 0.149 F1 (CV) 0.24 ±0.19 0.31 ±0.22 0.06 ±0.03 0.091 F2 (CV) 0.14 ±0.10 0.14 ±0.10 0.00 ±0.01 0.867 F3 (CV) 8.75 ±35.36 23.86 ±96.34 15.11 ±60.97 0.317 ER (Q2) 8.17 ±32.52 8.07 ±32.42 −0.10 ± −0.10 0.989 ER (CV) 0.64 ±0.39 0.61 ±0.36 −0.03 ± −0.02 0.705 F0 (CV) 0.40 ±0.91 0.63 ±1.81 0.24 ±0.89 0.434 GNE (Q2) −0.91 ±2.72 −1.25 ±3.11 −0.35 ±0.39 0.582 GNE (SD) 0.30 ±0.75 0.39 ±0.90 0.09 ±0.15 0.580 TEO (CV) −0.74 ±3.27 −0.28 ±1.30 0.46 ± −1.97 0.376 NNE (Q2) −0.19 ±0.79 −0.11 ±0.47 0.09 ± −0.31 0.530 NNE (SD) 1.62 ±0.83 1.58 ±0.91 −0.04 ±0.08 0.843 vowel /u/ PPQ 1.35 ±1.17 2.60 ±3.07 1.26 ±1.90 0.009 APQ 12.66 ±5.60 17.03 ±9.50 4.37 ±3.91 0.007 FLUF 2.77 ±5.13 8.52 ±9.83 5.75 ±4.69 0.001 HNR (Q2) 15.28 ±4.23 14.32 ±5.22 −0.96 ±0.99 0.270 HNR (SD) 5.40 ±1.56 5.08 ±1.46 −0.32 ± −0.10 0.252 F1 (CV) 0.69 ±0.44 0.71 ±0.34 0.03 ± −0.10 0.667 F2 (CV) 0.17 ±0.09 0.18 ±0.09 0.01 ± −0.00 0.468 F3 (CV) 10.28 ±52.21 15.04 ±104.80 4.76 ±52.58 0.779 ER (Q2) 8.27 ±33.82 3.63 ±25.29 −4.64 ± −8.53 0.453 ER (CV) 0.67 ±0.39 0.74 ±0.43 0.06 ±0.04 0.431 F0 (CV) 0.23 ±0.67 0.18 ±0.10 −0.05 ± −0.57 0.586 GNE (Q2) −0.19 ±1.31 0.00 ±0.00 0.19 ± −1.31 0.323 GNE (SD) 0.09 ±0.40 0.10 ±0.70 0.01 ±0.30 0.966 TEO (CV) −0.51 ±2.69 −0.07 ±0.51 0.43 ± −2.18 0.275 NNE (Q2) −1.27 ±7.09 −0.31 ±2.190 0.96 ± −4.91 0.373 NNE (SD) 1.57 ±0.73 1.68 ±0.49 0.11 ± −0.24 0.379 The results of Spearman’s partial correlation between the baseline acoustic features (session 1) and change in clinical data ( ∆ ) can be seen in Table 3. None of the features significantly correlated with UPDRS, part III. On the other hand, in the case of part IV, we can observe negative correlation with aperiodicity (FLUF, vowels /e/, /i/, /o/, /u/), i.e., low aperiodicity at the baseline resulted in increased complications with therapy. Similarly, we identified negative correlation with tremor of jaw (F2 (CV), vowel /a/), but positive correlation with the tremor of lips (F3 (CV), vowel /o/). Another positive correlations were observed with median of energy ratio (vowels /o/, /u/), irregular pitch fluctuations (F0 (CV), vowel /a/), and variability of voice quality (GNE (SD), vowel /a/). Change in UPDRSIV negatively correlated with irregular amplitude fluctuations (TEO (CV), vowel /u/), acoustic noise (NNE (Q2), vowel /u/) and its variation (NNE (SD), vowel /a/). Results linked with the acoustic noise quantified by the median GNE are not consistent. RBDSQ significantly and positively correlated with microperturbations in frequency of voice (PPQ, vowel /u/) and microperturbations of its intensity (APQ, vowel /a/), i.e., increased microperturbations in frequency/amplitude at the baseline resulted in deterioration of sleep. In addition, RBDSQ negatively correlated with the variation of voice quality (HNR (SD), vowel /o/). Regarding gait difficulties, as assessed by FOG-Q, we can observe two positive correlations with tremor of jaw (F1 (CV), vowel /i/) and irregular pitch fluctuations (F0 (CV), vowel /a/). The total score of this questionnaire negatively correlates with variation of acoustic noise (NNE (SD), vowel /o/). Appl. Sci. 2018,8, 2339 9 of 18 Table 3. Spearman’s correlation coefficients between baseline acoustic features and ∆of clinical data. Feature /a/ /e/ /i/ /o/ /u/ /a/ /e/ /i/ /o/ /u/ UPDRSIII UPDRSIV PPQ −0.07 −0.08 0.26 −0.09 −0.10 −0.11 −0.26 −0.08 −0.17 −0.08 APQ −0.06 −0.05 0.17 −0.10 −0.09 0.08 0.12 −0.01 0.06 −0.09 FLUF 0.10 0.08 0.11 0.10 0.16 −0.23 −0.47 ** −0.33 * −0.34 * −0.32 * HNR (Q2) 0.16 0.07 −0.05 0.17 0.09 −0.02 −0.08 0.07 0.11 0.16 HNR (SD) 0.10 0.11 −0.04 −0.05 −0.15 0.07 −0.02 0.20 −0.22 −0.09 F1 (CV) 0.04 0.10 −0.17 −0.02 0.19 −0.27 −0.07 0.08 −0.32 * 0.08 F2 (CV) −0.15 0.20 −0.10 −0.11 0.11 −0.37 * −0.11 −0.12 −0.23 0.04 F3 (CV) −0.24 0.25 −0.23 −0.17 0.11 0.22 0.28 0.10 0.32 * 0.10 ER (Q2) −0.25 0.25 −0.14 −0.17 0.17 0.16 0.28 0.12 0.34 * 0.32 * ER (CV) 0.12 −0.09 0.22 −0.03 0.11 −0.17 −0.14 −0.22 −0.18 −0.06 F0 (CV) 0.28 −0.12 0.04 −0.08 0.17 0.33 * −0.04 −0.24 −0.16 −0.21 GNE (Q2) −0.14 0.11 −0.15 0.06 −0.17 −0.35 * 0.25 0.15 0.27 0.33 * GNE (SD) −0.16 −0.08 −0.12 −0.22 0.24 0.30 * −0.01 −0.04 0.22 0.11 TEO (CV) 0.28 −0.25 0.11 0.15 −0.25 −0.23 −0.28 −0.28 −0.23 −0.30 * NNE (Q2) 0.28 −0.25 −0.09 0.14 −0.23 −0.15 −0.28 −0.22 −0.26 −0.31 * NNE (SD) 0.09 −0.25 0.12 0.11 −0.26 −0.43 ** −0.17 −0.28 −0.12 −0.12 RBDSQ FOG-Q PPQ 0.15 0.11 0.21 −0.13 0.33 * −0.20 −0.09 0.15 −0.09 0.08 APQ 0.29 * 0.27 0.21 0.27 0.20 −0.18 −0.14 −0.16 −0.16 −0.12 FLUF −0.06 0.06 −0.22 −0.17 −0.24 0.20 0.15 0.13 0.17 0.23 HNR (Q2) −0.20 −0.17 −0.19 −0.27 −0.20 0.09 0.03 −0.03 0.09 −0.05 HNR (SD) −0.17 −0.16 0.21 −0.36 * −0.27 0.07 0.24 0.21 0.18 0.12 F1 (CV) 0.08 −0.02 0.24 0.09 0.11 0.16 −0.22 0.33 * −0.20 −0.20 F2 (CV) −0.08 −0.09 −0.26 −0.17 −0.27 0.18 −0.09 −0.03 −0.13 0.26 F3 (CV) −0.10 −0.04 −0.11 0.07 −0.08 0.03 0.22 0.14 0.08 −0.11 ER (Q2) −0.19 −0.21 −0.26 −0.12 −0.16 −0.13 0.04 0.25 0.10 −0.05 ER (CV) 0.08 0.28 0.20 −0.28 −0.11 0.04 −0.13 −0.11 0.10 0.06 F0 (CV) 0.21 0.13 0.19 0.25 0.10 0.37 * 0.20 −0.03 −0.10 0.19 GNE (Q2) −0.16 −0.17 −0.28 −0.18 −0.16 −0.29 −0.25 0.05 −0.19 −0.19 GNE (SD) −0.05 −0.09 −0.25 0.09 −0.20 0.08 0.14 −0.05 0.12 0.15 TEO (CV) 0.05 0.04 0.27 −0.17 0.15 −0.05 −0.22 −0.07 −0.25 −0.01 NNE (Q2) 0.24 0.28 0.18 0.20 0.21 −0.04 0.21 0.17 0.16 0.20 NNE (SD) −0.27 −0.05 −0.19 −0.16 0.11 −0.23 −0.12 0.16 −0.22 ** 0.05 *— p -value of Spearman’s correlation coefficient <0.05; **— p -value of Spearman’s correlation coefficient <0.01. The results of Spearman’s partial correlation between the change of baseline acoustic features ( ∆ ) and the change in clinical data ( ∆ ) can be seen in Table 4. Regarding the change of UPDRSIII, it negatively correlated with the change of microperturbations in frequency of voice (PPQ, vowel /i/), aperiodicity (FLUF, vowels /e/, /o/), tremor of tongue (F1 (CV), vowels /a/, /u/), tremor of jaw (F2 (CV), vowel /e/), irregular pitch fluctuations (F0 (CV), vowels /a/, /u/), and variation of acoustic noise (NNE (SD), vowel /i/). Significant positive correlations were identified with the change of lips tremor (F3 (CV), vowel /a/), acoustic noise (ER (Q2), vowel /a/), and variation of voice quality (GNE (SD), vowel /e/). In the case of UPDRSIV, we identified seven significant positive correlations with the change of microperturbations in frequency of voice (PPQ, vowel /e/), tremor of jaw (F2 (CV), vowel /a/), irregular amplitude fluctuations (TEO (CV), vowels /a/, /u/), and acoustic noise (NNE (Q2), vowels /o/, /u/). The change in UPDRS IV significantly negatively correlated with the change of acoustic noise (ER (Q2), vowel /u/), and its variation (ER (CV), vowel /e/). Changes in RBDSQ significantly negatively correlated with the change of microperturbations in frequency of voice (PPQ, vowel /u/), microperturbations of its intensity (APQ, vowels /e/, /i/, /u/), tremor of lips (F3 (CV), vowel /o/), acoustic noise (NNE (Q2), vowel /e/), and its variation (ER (CV), vowel /e/). Positive correlations were identified with the change in voice quality (HNR (Q2), all vowels) and its variability (HNR (SD), vowels /e/, /o/, /u/). The similar results can be observed when assessing the quality by GNE (vowel /e/). Appl. Sci. 2018,8, 2339 16 of 18 11. Elfmarkova, N.; Gajdos, M.; Mrackova, M.; Mekyska, J.; Mikl, M.; Rektorova, I. Impact of Parkinson’s disease and levodopa on resting state functional connectivity related to speech prosody control. Parkinsonism Relat. Disord. 2016,22 (Suppl. 1), S52–S55. [CrossRef] [PubMed] 12. Gómez-Vilda, P.; Mekyska, J.; Ferrández, J.M.; Palacios-Alonso, D.; Gómez-Rodellar, A.; Rodellar-Biarge, V.; Galaz, Z.; Smekal, D.; Rektorova, I.; Eliasova, I.; et al. Parkinson Disease Detection from Speech Articulation Neuromechanics. Front. Neuroinform. 2017,11, 56. [CrossRef] [PubMed] 13. Lirani-Silva, C.; Mourão, L.F.; Gobbi, L.T.B. Dysarthria and Quality of Life in neurologically healthy elderly and patients with Parkinson’s disease. CoDAS 2015,27, 248–254. [CrossRef] [PubMed] 14. Ho, A.K.; Iansek, R.; Marigliani, C.; Bradshaw, J.L.; Gates, S. Speech Impairment in a Large Sample of Patients with Parkinson’s disease. J. Behav. Neurol. 1999,11, 131–137. [CrossRef] 15. Tsanas, A.; Little, M.; McSharry, P.; Ramig, L. Accurate telemonitoring of Parkinson’s Disease progression by noninvasive speech tests. IEEE Trans. Bio-Med. Eng. 2010,57, 884–893. [CrossRef] [PubMed] 16. Harel, B.T.; Cannizzaro, M.S.; Cohen, H.; Reilly, N.; Snyder, P.J. Acoustic characteristics of Parkinsonian speech: A potential biomarker of early disease progression and treatment. J. Neurolinguist. 2004 ,17, 439–453. [CrossRef] 17. Rusz, J.; Cmejla, R.; Ruzickova, H.; Klempir, J.; Majerova, V.; Picmausova, J.; Roth, J.; Ruzicka, E. Evaluation of speech impairment in early stages of Parkinson’s disease: A prospective study with the role of pharmacotherapy. J. Neural Transm. 2013,120, 319–329. [CrossRef] [PubMed] 18. Skodda, S.; Grönheit, W.; Schlegel, U.; Südmeyer, M.; Schnitzler, A.; Wojtecki, L. Effect of subthalamic stimulation on voice and speech in Parkinson’s disease: For the better or worse? Front. Neurol. 2014 ,4, 218. [CrossRef] [PubMed] 19. Orozco-Arroyave, J.R.; Hönig, F.; Arias-Londoño, J.D.; Vargas-Bonilla, J.F.; Daqrouq, K.; Skodda, S.; Rusz, J.; Nöth, E. Automatic detection of Parkinson’s disease in running speech spoken in three different languages. J. Acoust. Soc. Am. 2016,139, 481–500. [CrossRef] [PubMed] 20. Mekyska, J.; Smekal, Z.; Galaz, Z.; Mzourek, Z.; Rektorova, I.; Faundez-Zanuy, M.; López-de Ipiña, K. Perceptual features as markers of Parkinson’s Disease: the issue of clinical interpretability. In Recent Advances in Nonlinear Speech Processing; Springer: New York, NY, USA, 2016; pp. 83–91. 21. Mekyska, J.; Galaz, Z.; Mzourek, Z.; Smekal, Z.; Rektorova, I.; Eliasova, I.; Kostalova, M.; Mrackova, M.; Berankova, D.; Faundez-Zanuy, M.; et al. Assessing progress of Parkinson’s disease using acoustic analysis of phonation. In Proceedings of the 2015 4th International Work Conference on Bioinspired Intelligence (IWOBI), San Sebastian, Spain, 10–12 June 2015; pp. 111–118. 22. Arora, S.; Venkataraman, V.; Zhan, A.; Donohue, S.; Biglan, K.; Dorsey, E.; Little, M. Detecting and monitoring the symptoms of Parkinson’s disease using smartphones: A pilot study. Parkinsonism Relat. Disord. 2015 , 21, 650–653. [CrossRef] [PubMed] 23. Villa-Cañas, T.; Orozco-Arroyave, J.; Vargas-Bonilla, J.; Arias-Londoño, J. Modulation spectra for automatic detection of Parkinson’s disease. In Proceedings of the 2014 XIX Symposium on Image, Signal Processing and Artificial Vision (STSIVA), Armenia, Colombia, 17–19 September 2014; pp. 1–5. 24. Hazan, H.; Hilu, D.; Manevitz, L.; Ramig, L.O.; Sapir, S. Early diagnosis of Parkinson’s disease via machine learning on speech data. In Proceedings of the 2012 IEEE 27th Convention of Electrical & Electronics Engineers in Israel (IEEEI), Eilat, Israel, 14–17 November 2012; pp. 1–4. 25. Eskidere, Ö.; Erta¸s, F.; Hanilçi, C. A comparison of regression methods for remote tracking of Parkinson’s disease progression. Expert Syst. Appl. 2012,39, 5523–5528. [CrossRef] 26. Castelli, M.; Vanneschi, L.; Silva, S. Prediction of the Unified Parkinson’s Disease Rating Scale assessment using a genetic programming system with geometric semantic genetic operators. Expert Syst. Appl. 2014 , 41, 4608–4616. [CrossRef] 27. Naranjo, L.; Pérez, C.J.; Martín, J. Addressing voice recording replications for tracking Parkinson’s disease progression. Med. Biol. Eng. Comput. 2017,55, 365–373. [CrossRef] [PubMed] 28. Skodda, S.; Rinsche, H.; Schlegel, U. Progression of dysprosody in Parkinson’s disease over time—A longitudinal study. Mov. Disord. 2009,24, 716–722. [CrossRef] [PubMed] 29. Skodda, S.; Flasskamp, A.; Schlegel, U. Instability of syllable repetition as a marker of disease progression in Parkinson’s disease: A longitudinal study. Mov. Disord. 2011,26, 59–64. [CrossRef] [PubMed] 30. Skodda, S.; Grönheit, W.; Schlegel, U. Impairment of vowel articulation as a possible marker of disease progression in Parkinson’s disease. PLoS ONE 2012,7, e32132. [CrossRef] [PubMed] Appl. Sci. 2018,8, 2339 17 of 18 31. Skodda, S.; Gronheit, W.; Mancinelli, N.; Schlegel, U. Progression of Voice and Speech Impairment in the Course of Parkinson’s Disease: A Longitudinal Study. Parkinson’s Dis. 2013 ,2013, 389195. [CrossRef] [PubMed] 32. Lee, J.Y.; Kim, J.W.; Lee, W.Y.; Kim, J.M.; Ahn, T.B.; Kim, H.J.; Cho, J.; Jeon, B.S. Daily dose of dopaminergic medications in Parkinson’s disease: clinical correlates and a posteriori equation. Neurol. Asia 2010 , 15, 137–143. 33. Stiasny-Kolster, K.; Mayer, G.; Schafer, S.; Muller, J.C.; Heinzel-Gutenbrunner, M.; Oertel, W.H. The REM sleep behavior disorder screening questionnaire—A new diagnostic instrument. Mov. Disord. 2007 , 22, 2386–2393. [CrossRef] [PubMed] 34. Mol, H. Lossfree Twin-Tube Resonator and the Vowel Triangle of Hellwag. J. Acoust. Soc. Am. 1965 ,37, 1186. [CrossRef] 35. Orozco-Arroyave, J.R.; Hönig, F.; Arias-Londoño, J.D.; Vargas-Bonilla, J.; Skodda, S.; Rusz, J.; Nöth, E. Automatic detection of Parkinson’s disease from words uttered in three different languages. In Proceedings of the Fifteenth Annual Conference of the International Speech Communication Association, Singapore, 14–18 September 2014; pp. 1573–1577. 36. Rusz, J.; Cmejla, R.; Tykalova, T.; Ruzickova, H.; Klempir, J.; Majerova, V.; Picmausova, J.; Roth, J.; Ruzicka, E. Imprecise vowel articulation as a potential early marker of Parkinson’s disease: Effect of speaking task. J. Acoust. Soc. Am. 2013,134, 2171–2181. [CrossRef] [PubMed] 37. Rusz, J.; Cmejla, R.; Ruzickova, H.; Ruzicka, E. Quantitative acoustic measurements for characterization of speech and voice disorders in early untreated Parkinson’s disease. J. Acoust. Soc. Am. 2011 ,129, 350–367. [CrossRef] [PubMed] 38. Titze, I.R. Principles of Voice Production; Prentice Hall: Englewood Cliffs, NJ, USA, 1994. 39. Harar, P.; Alonso-Hernandezy, J.B.; Mekyska, J.; Galaz, Z.; Burget, R.; Smekal, Z. Voice Pathology Detection Using Deep Learning: A Preliminary Study. In Proceedings of the 2017 International Conference and Workshop on Bioinspired Intelligence (IWOBI), Funchal, Portugal, 10–12 July 2017; pp. 45–48. 40. Harar, P.; Galaz, Z.; Alonso-Hernandez, J.B.; Mekyska, J.; Burget, R.; Smekal, Z. Towards robust voice pathology detection. Neural Comput. Appl. 2018. [CrossRef] 41. Kostalova, M.; Mrackova, M.; Marecek, R.; Berankova, D.; Eliasova, I.; Janousova, E.; Roubickova, J.; Bednarik, J.; Rektorova, I. The 3F Test Dysarthric Profile—Normative Speach Values in Czech. Ceska Slovenska Neurologie Neurochirurgie 2013,76, 614–618. 42. Boersma, P.; Weenink, D. Praat, a system for doing phonetics by computer. Glot Int. 2002,5, 341–345. 43. Mekyska, J.; Janousova, E.; Gomez-Vilda, P.; Smekal, Z.; Rektorova, I.; Eliasova, I.; Kostalova, M.; Mrackova, M.; Alonso-Hernandez, J.B.; Faundez-Zanuy, M.; et al. Robust and complex approach of pathological speech signal analysis. Neurocomputing 2015,167, 94–111. [CrossRef] 44. Rektorova, I.; Mekyska, J.; Janousova, E.; Kostalova, M.; Eliasova, I.; Mrackova, M.; Berankova, D.; Necasova, T.; Smekal, Z.; Marecek, R. Speech prosody impairment predicts cognitive decline in Parkinson’s disease. Parkinsonism Relat. Disord. 2016,29, 90–95. [CrossRef] [PubMed] 45. Arias-Vergara, T.; Vásquez-Correa, J.C.; Orozco-Arroyave, J.R. Parkinson’s Disease and Aging: Analysis of Their Effect in Phonation and Articulation of Speech. Cogn. Comput. 2017,9, 731–748. [CrossRef] 46. Rusz, J.; Tykalova, T.; Klempir, J.; Cmejla, R.; Ruzicka, E. Effects of dopaminergic replacement therapy on motor speech disorders in Parkinson’s disease: Longitudinal follow-up study on previously untreated patients. J. Neural Transm. 2016,123, 379–387. [CrossRef] [PubMed] 47. Chen, T.; Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA, 13–17 August 2016; pp. 785–794. 48. Breiman, L.; Friedman, J.H.; Olshen, R.A.; Stone, C.J. Classification and Regression Trees; Wadsworth and Brooks: Monterey, CA, USA, 1984. 49. Torlay, L.; Perrone-Bertolotti, M.; Thomas, E.; Baciu, M. Machine learning—XGBoost analysis of language networks to classify patients with epilepsy. Brain Inform. 2017,4, 159. [CrossRef] [PubMed] 50. Chen, Y.; Wang, X.; Jung, Y.; Abedi, V.; Zand, R.; Bikak, M.; Adibuzzaman, M. Classification of short single lead electrocardiograms (ECGs) for atrial fibrillation detection using piecewise linear spline and XGBoost. Physiol. Meas. 2018,39, 104006. [CrossRef] [PubMed] Appl. Sci. 2018,8, 2339 18 of 18 51. Zhong, J.; Sun, Y.; Peng, W.; Xie, M.; Yang, J.; Tang, X. XGBFEMF: An XGBoost-based Framework for Essential Protein Prediction. IEEE Trans. NanoBiosci. 2018,17, 243–250. [CrossRef] [PubMed] 52. Palmer, J.L.; Coats, M.A.; Roe, C.M.; Hanko, S.M.; Xiong, C.; Morris, J.C. Unified Parkinson’s Disease Rating Scale-Motor Exam: Inter-rater reliability of advanced practice nurse and neurologist assessments. J. Adv. Nurs. 2010,66, 1382–1387. [CrossRef] [PubMed] 53. Baggio, J.A.O.; Curtarelli, M.B.; Rodrigues, G.R.; Tumas, V. Validity of the Brazilian version of the freezing of gait questionnaire. Arquivos de Neuro-Psiquiatria 2012,70, 599–603. [CrossRef] [PubMed] 54. Santos, D.G.; Macías, M.A. Inter-rater variability in motor function assessment in Parkinson’s disease between experts in movement disorders and nurses specialising in PD management. Neurologia 2017 . [CrossRef] 55. Jankovic, J. Parkinson’s disease: Clinical features and diagnosis. J. Neurol. Neurosurg. Psychiatry 2008 , 79, 368–376. [CrossRef] [PubMed] 56. Mekyska, J.; Galaz, Z.; Kiska, T.; Zvoncak, V.; Mucha, J.; Smekal, Z.; Eliasova, I.; Kostalova, M.; Mrackova, M.; Fiedorova, D.; et al. Quantitative Analysis of Relationship Between Hypokinetic Dysarthria and the Freezing of Gait in Parkinson’s Disease. Cogn. Comput. 2018. [CrossRef] 57. Berg, D.; Postuma, R.B.; Adler, C.H.; Bloem, B.R.; Chan, P.; Dubois, B.; Gasser, T.; Goetz, C.G.; Halliday, G.; Joseph, L.; et al. MDS research criteria for prodromal Parkinson’s disease. Mov. Dis. 2015 ,30, 1600–1611. [CrossRef] [PubMed] c 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).