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

Machine learning-based classification of Parkinson's disease using acoustic features: Insights from multilingual speech tasks

This study advances the automation of Parkinson's disease (PD) diagnosis by analyzing speech characteristics, leveraging a comprehensive approach that integrates a voting-based machine learning model. Given the growing prevalence of PD, especially among the elderly population, continuous and efficient diagnosis is of paramount importance. Conventional monitoring methods suffer from limitations related to time, cost, and accessibility, underscoring the need for the development of automated diagnostic tools. In this paper, we present a robust model for classifying speech patterns in Korean PD patients, addressing a significant research gap. Our model employs straightforward preprocessing techniques and a voting-based machine learning approach, demonstrating superior performance, particularly when training data is limited. Furthermore, we emphasize the effectiveness of the eGeMAPSv2 feature set in PD analysis and introduce new features that substantially enhance classification accuracy. The proposed model, achieving an accuracy of 84.73 % and an area under the ROC (AUC) score of 92.18 % on a dataset comprising 100 Korean PD patients and 100 healthy controls, offers a practical solution for automated diagnosis applications, such as smartphone apps. Future research endeavors will concentrate on enhancing the model's performance and delving deeper into the relationship between high-importance features and PD.

A study on the correlations between acoustic speech variables and bradykinesia in advanced Parkinson's disease

Background

Very few studies have assessed the presence of a possible correlation between speech variables and limb bradykinesia in patients with Parkinson's disease (PD). The objective of this study was to find correlations between different speech variables and upper extremity bradykinesia under different medication conditions in advanced PD patients.

Methods

Retrospective data were collected from a cohort of advanced PD patients before and after an acute levodopa challenge. Each patient was assessed with a perceptual-acoustic analysis of speech, which included several quantitative parameters [i.e., maximum phonation time (MPT) and intensity (dB)]; the Unified Parkinson's Disease Rating Scale (UPDRS) (total scores, subscores, and items); and a timed test (a tapping test for 20 s) to quantify upper extremity bradykinesia. Pearson's correlation coefficient was applied to find correlations between the different speech variables and the tapping rate.

Results

A total of 53 PD patients [men: 34; disease duration: 10.66 (SD 4.37) years; age at PD onset: 49.81 years (SD 6.12)] were included. Levodopa intake increased the MPT of sustained phonation (p < 0.01), but it reduced the speech rate (p = 0.05). In the defined-OFF condition, MPT of sustained phonation positively correlated with both bilateral mean (p = 0.044, r-value:0.299) and left (p = 0.033, r-value:0.314) tapping. In the defined-ON condition, the MPT correlated positively with bilateral mean tapping (p = 0.003), left tapping (p = 0.003), and right tapping (p = 0.008).

Conclusion

This study confirms the presence of correlations between speech acoustic variables and upper extremity bradykinesia in advanced PD patients. These findings suggest common pathophysiological mechanisms.

Classification of Dysphonic Voices in Parkinson's Disease with Semi-Supervised Competitive Learning Algorithm

This article proposes a novel semi-supervised competitive learning (SSCL) algorithm for vocal pattern classifications in Parkinson’s disease (PD). The acoustic parameters of voice records were grouped into the families of jitter, shimmer, harmonic-to-noise, frequency, and nonlinear measures, respectively. The linear correlations were computed within each acoustic parameter family. According to the correlation matrix results, the jitter, shimmer, and harmonic-to-noise parameters presented as highly correlated in terms of Pearson’s correlation coefficients. Then, the principal component analysis (PCA) technique was implemented to eliminate the redundant dimensions of the acoustic parameters for each family. The Mann−Whitney−Wilcoxon hypothesis test was used to evaluate the significant difference of the PCA-projected features between the healthy subjects and PD patients. Eight dominant PCA-projected features were selected based on the eigenvalue threshold criterion and the statistical significance level (p < 0.05) of the hypothesis test. The SSCL algorithm proposed in this paper included the procedures of the competitive prototype seed selection, K-means optimization, and the nearest neighbor classifications. The pattern classification experimental results showed that the proposed SSCL method can provide the excellent diagnostic performances in terms of accuracy (0.838), recall (0.825), specificity (0.85), precision (0.846), F-score (0.835), Matthews correlation coefficient (0.675), area under the receiver operating characteristic curve (0.939), and Kappa coefficient (0.675), which were consistently better than those results of conventional KNN or SVM classifiers.

Objective quantification of the severity of postural tremor based on kinematic parameters: A multi-sensory fusion study

BACKGROUND

Current clinical assessments of essential tremor (ET) are primarily based on expert consultation combined with reviewing patient complaints, physician expertise, and diagnostic experience. Thus, traditional evaluation methods often lead to biased diagnostic results. There is a clinical demand for a method that can objectively quantify the severity of the patient's disease.

METHODS

This study aims to develop an artificial intelligence-aided diagnosis method based on multi-sensory fusion wearables. The experiment relies on a rigorous clinical trial paradigm to collect multi-modal fusion of signals from 98 ET patients. At the same time, three clinicians scored independently, and the consensus score obtained was used as the ground truth for the machine learning models.

RESULTS

Sixty kinematic parameters were extracted from the signals recorded by the nine-axis inertial measurement unit (IMU). The results showed that most of the features obtained by IMU could effectively characterize the severity of the tremors. The accuracy of the optimal model for three tasks classifying five severity levels was 97.71%, 97.54%, and 97.72%, respectively.

CONCLUSIONS

This paper reports the first attempt to combine multiple feature selection and machine learning algorithms for fine-grained automatic quantification of postural tremor in ET patients. The promising results showed the potential of the proposed approach to quantify the severity of ET objectively.

Parkinson's disease patients with freezing of gait have more severe voice impairment than non-freezers during "ON state"

BACKGROUND

Speech disorders and freezing of gait (FOG) in Parkinson's disease (PD) may have some common pathological mechanisms. The purpose of this study was to compare the acoustic parameters of PD patients with dopamine-responsive FOG (PD-FOG) and without FOG (PD-nFOG) during "ON state" and explore the ability of "ON state" voice features in distinguishing PD-FOG from PD-nFOG.

METHODS

A total of 120 subjects, including 40 PD patients with dopamine-responsive FOG, 40 PD-nFOG, and 40 healthy controls (HCs) were recruited. All subjects underwent neuropsychological tests. Speech samples were recorded through the sustained vowel pronunciation tasks during the "ON state" and then analyzed by the Praat software. A set of 27 voice features was extracted from each sample for comparison. Support vector machine (SVM) was used to build mathematical models to classify PD-FOG and PD-nFOG.

RESULTS

Compared with PD-nFOG, the jitter, the standard deviation of fundamental frequency (F0SD), the standard deviation of pulse period (pulse period SD) and the noise-homophonic-ratio (NHR) were increased, and the maximum phonation time (MPT) was decreased in PD-FOG. The above voice features were correlated with the freezing of gait questionnaire (FOGQ). The average accuracy, specificity, and sensitivity of SVM models based on 27 voice features for classifying PD-FOG and PD-nFOG were 73.57%, 75.71%, and 71.43%, respectively.

CONCLUSIONS

PD-FOG have more severe voice impairment than PD-nFOG during "ON state".

Objective vowel sound characteristics and their relationship with motor dysfunction in Asian Parkinson's disease patients

BACKGROUND

Speech impairments are very common in patients with Parkinson's disease (PD). However, knowledge of their objective characteristics and relationship to other motor symptoms amongst Asian PD patients is limited.

OBJECTIVES

To identify objective vowel sound characteristics in Thai PD patients and correlate with disease severity, as determined by UPDRS and various sub-scores.

METHOD

We evaluated 100 Thai PD patients, with a mean age of 66.56 years (±7.52) and HY of 2.7 (±1.08), and 101 age-matched controls. Phonatory evaluation, comprising of 15 objective parameters, was conducted using the Multi-Dimensional Voice Programme with a sustained /a/ phonation.

RESULTS

PD patients exhibited significantly higher values of all dimensions of the phonatory parameters evaluated compared to controls (All, p < 0.001) except for duration of sustained phonation, which was significantly shorter in PD patients. When early- and advanced-stage patients were compared, significantly different parameters were limited to frequency perturbation parameters (Jitt, p = 0.01; RAP, p = 0.013; PPQ, p = 0.01; sPPQ, p = 0.001; vF0, p = 0.011), and NHR (p = 0.028). Several significant and moderate correlations were observed between both STD and frequency perturbation parameters and UPDRS-III, bradykinesia sub-score, and gait and postural instability sub-score. Both vF0, and STD significantly correlated with UPDRS-III and sub-scores in advanced stage patients.

CONCLUSION

Our study provides objective evidence of phonatory dysfunction in Asian PD patients with certain characteristics correlated with advanced stage or different motor dysfunction. Sustained vowel phonation is a promising digital outcome for global phenotyping a large number of PD patients.

Voice changes in Parkinson's disease: What are they telling us?

Emerging evidence suggests voice dysfunction is the earliest sign of motor impairment in Parkinson's disease (PD). The complexity and fine motor control involved in vocalization may result in dysfunction here before the limbs. The voice in PD demonstrates characteristic changes on perceptual and acoustic analyses. The physiological and anatomical correlates of these have been investigated through laryngoscopy, stroboscopy, photoglottography, laryngeal electromyography, computed-tomography, pulmonary function testing and aerodynamic assessments. These have revealed numerous abnormalities including incomplete glottic closure and vocal fold hypoadduction/bowing to account for these voice changes. Many of these phenomena are likely related to rigidity or bradykinesia of the laryngeal muscles. The early onset of voice changes is resonant with the pathophysiological insights offered by Braak's hypothesis and murine models of the disease. These physiological abnormalities and pathological models largely stand to support dopaminergic and non-dopaminergic mechanisms being implicated in the pathogenesis of voice dysfunction. This review focuses on characterizing the voice changes in PD. These stand as a promising area of enquiry to further our understanding of the pathophysiology of the disease and offer potential to be utilized as an early diagnostic biomarker or marker of disease progression.

Wearable Sensors for Estimation of Parkinsonian Tremor Severity during Free Body Movements

Tremor is one of the main symptoms of Parkinson's Disease (PD) that reduces the quality of life. Tremor is measured as part of the Unified Parkinson Disease Rating Scale (UPDRS) part III. However, the assessment is based on onsite physical examinations and does not fully represent the patients' tremor experience in their day-to-day life. Our objective in this paper was to develop algorithms that, combined with wearable sensors, can estimate total Parkinsonian tremor as the patients performed a variety of free body movements. We developed two methods: an ensemble model based on gradient tree boosting and a deep learning model based on long short-term memory (LSTM) networks. The developed methods were assessed on gyroscope sensor data from 24 PD subjects. Our analysis demonstrated that the method based on gradient tree boosting provided a high correlation (r = 0.96 using held-out testing and r = 0.93 using subject-based, leave-one-out cross-validation) between the estimated and clinically assessed tremor subscores in comparison to the LSTM-based method with a moderate correlation (r = 0.84 using held-out testing and r = 0.77 using subject-based, leave-one-out cross-validation). These results indicate that our approach holds great promise in providing a full spectrum of the patients' tremor from continuous monitoring of the subjects' movement in their natural environment.