Speech disorders in Parkinson’s disease: early diagnostics and effects of medication and brain stimulation

Artificial intelligence-based framework to identify the abnormalities in the COVID-19 disease and other common respiratory diseases from digital stethoscope data using deep CNN

The utilization of lung sounds to diagnose lung diseases using respiratory sound features has significantly increased in the past few years. The Digital Stethoscope data has been examined extensively by medical researchers and technical scientists to diagnose the symptoms of respiratory diseases. Artificial intelligence-based approaches are applied in the real universe to distinguish respiratory disease signs from human pulmonary auscultation sounds. The Deep CNN model is implemented with combined multi-feature channels (Modified MFCC, Log Mel, and Soft Mel) to obtain the sound parameters from lung-based Digital Stethoscope data. The model analysis is observed with max-pooling and without max-pool operations using multi-feature channels on respiratory digital stethoscope data. In addition, COVID-19 sound data and enriched data, which are recently acquired data to enhance model performance using a combination of L2 regularization to overcome the risk of overfitting because of less respiratory sound data, are included in the work. The suggested DCNN with Max-Pooling on the improved dataset demonstrates cutting-edge performance employing a multi-feature channels spectrogram. The model has been developed with different convolutional filter sizes (1 × 12 , 1 × 24 , 1 × 36 , 1 × 48 , and 1 × 60 ) that helped to test the proposed neural network. According to the experimental findings, the suggested DCNN architecture with a max-pooling function performs better to identify respiratory disease symptoms than DCNN without max-pooling. In order to demonstrate the model's effectiveness in categorization, it is trained and tested with the DCNN model that extract several modalities of respiratory sound data.

In Silico Decoding of Parkinson's: Speech & Writing Analysis

Background: Parkinson's disease (PD) has transitioned from a rare condition in 1817 to the fastest-growing neurological disorder globally. The significant increase in cases from 2.5 million in 1990 to 6.1 million in 2016, coupled with predictions of a further doubling by 2040, underscores an impending healthcare challenge. This escalation aligns with global demographic shifts, including rising life expectancy and a growing global population. The economic impact, notably in the U.S., reached $51.9 billion in 2017, with projections suggesting a 46% increase by 2037, emphasizing the substantial socio-economic implications for both patients and caregivers. Coupled with a worldwide demand for health workers that is expected to rise to 80 million by 2030, we have fertile ground for a pandemic. Methods: Our transdisciplinary research focused on early PD detection through running speech and continuous handwriting analysis, incorporating medical, biomedical engineering, AI, and linguistic expertise. The cohort comprised 30 participants, including 20 PD patients at stages 1-4 on the Hoehn and Yahr scale and 10 healthy controls. We employed advanced AI techniques to analyze correlation plots generated from speech and handwriting features, aiming to identify prodromal PD biomarkers. Results: The study revealed distinct speech and handwriting patterns in PD patients compared to controls. Our ParkinsonNet model demonstrated high predictive accuracy, with F1 scores of 95.74% for speech and 96.72% for handwriting analyses. These findings highlight the potential of speech and handwriting as effective early biomarkers for PD. Conclusions: The integration of AI as a decision support system in analyzing speech and handwriting presents a promising approach for early PD detection. This methodology not only offers a novel diagnostic tool but also contributes to the broader understanding of PD's early manifestations. Further research is required to validate these findings in larger, diverse cohorts and to integrate these tools into clinical practice for timely PD pre-diagnosis and management.

Do Acoustic Characteristics of Dysarthria in People With Parkinson's Disease Differ Across Languages?

PURPOSE

Cross-language studies suggest more similarities than differences in how dysarthria affects the speech of people with Parkinson's disease (PwPD) who speak different languages. In this study, we aimed to identify the relative contribution of acoustic variables to distinguish PwPD from controls who spoke varieties of two Romance languages, French and Portuguese.

METHOD

This bi-national, cross-sectional, and case-controlled study included 129 PwPD and 124 healthy controls who spoke French or Portuguese. All participants underwent the same clinical examinations, voice/speech recordings, and self-assessment questionnaires. PwPD were evaluated off and on optimal medication. Inferential analyses included Disease (controls vs. PwPD) and Language (French vs. Portuguese) as factors, and random decision forest algorithms identified relevant acoustic variables able to distinguish participants: (a) by language (French vs. Portuguese) and (b) by clinical status (PwPD on and off medication vs. controls).

RESULTS

French-speaking and Portuguese-speaking individuals were distinguished from each other with over 90% accuracy by five acoustic variables (the mean fundamental frequency and the shimmer of the sustained vowel /a/ production, the oral diadochokinesis performance index, the relative sound level pressure and the relative sound pressure level standard deviation of the text reading). A distinct set of parameters discriminated between controls and PwPD: for men, maximum phonation time and the oral diadochokinesis speech proportion were the most significant variables; for women, variables calculated from the oral diadochokinesis were the most discriminative.

CONCLUSIONS

Acoustic variables related to phonation and voice quality distinguished between speakers of the two languages. Variables related to pneumophonic coordination and articulation rate were the more effective in distinguishing PwPD from controls. Thus, our research findings support that respiration and diadochokinesis tasks appear to be the most appropriate to pinpoint signs of dysarthria, which are largely homogeneous and language-universal. In contrast, identifying language-specific variables with the speech tasks and acoustic variables studied was less conclusive.

Neurocognitive functioning of patients with early-stage Parkinson's disease

Parkinson's disease (PD) is a neurological disorder commonly associated with motor deficits. However, cognitive impairment is also common in patients with PD. Cognitive concerns in PD may affect multiple domains of neurocognition and vary across different stages of the disease. Extant research has focused mainly on cognitive deficits in middle to late stages of PD, whereas few studies have examined the unique cognitive profiles of patients with early-stage PD. This study addressed this gap in the published literature and examined neurocognitive functioning and functional capacity of patients with de novo PD, focusing on the unique pattern of cognitive deficits specific to the early stage of the disease. Results indicated that the pattern of cognitive deficits in patients with PD (n = 55; mean age = 72.93) was significantly different from healthy controls (n = 59; mean age = 71.88). Specifically, tasks related to executive functioning, attention, and verbal memory demonstrated the most pronounced deficits in patients with early-stage PD. Clinical implications of these findings are discussed.

Vocal and tongue exercise in early to mid-stage Parkinson disease using the Pink1-/- rat

Vocal and swallowing deficits are common in Parkinson disease (PD). Because these impairments are resistant to dopamine replacement therapies, vocal and lingual exercise are the primary treatment, but not all individuals respond to exercise and neural mechanisms of treatment response are unclear. To explore putative mechanisms, we used the progressive Pink1-/- rat model of early to mid-stage PD and employed vocal and lingual exercises at 6- and 10-months of age in male Pink1-/- and wild type (WT) rats. We hypothesized that vocal and lingual exercise would improve vocal and tongue use dynamics and increase serotonin (5HT) immunoreactivity in related brainstem nuclei. Rats were tested at baseline and after 8 weeks of exercise or sham exercise. At early-stage PD (6 months), vocal exercise resulted in increased call complexity, but did not change intensity, while at mid-stage (10 months), vocal exercise no longer influenced vocalization complexity. Lingual exercise increased tongue force generation and reduced relative optical density of 5HT in the hypoglossal nucleus at both time points. The effects of vocal and lingual exercise at these time points are less robust than in prodromal stages observed in previous work, suggesting that early exercise interventions may yield greater benefit. Future work targeting optimization of exercise at later time points may facilitate clinical translation.

One side effect: two networks? Lateral and posteromedial stimulation spreads induce dysarthria in subthalamic deep brain stimulation for Parkinson's disease

BACKGROUND

Stimulation-induced dysarthria (SID) is a troublesome and potentially therapy-limiting side effect of deep brain stimulation of the subthalamic nucleus (STN-DBS) in patients with Parkinson's disease (PD). To date, the origin of SID, and especially whether there is an involvement of cerebellar pathways as well as the pyramidal tract, remains a matter of debate. Therefore, this study aims to shed light on structural networks associated with SID and to derive a data-driven model to predict SID in patients with PD and STN-DBS.

METHODS

Randomised, double-blinded monopolar reviews determining SID thresholds were conducted in 25 patients with PD and STN-DBS. A fibre-based mapping approach, implementing the calculation of fibr-wise ORs for SID, was employed to identify the distributional pattern of SID in the STN's vicinity. The ability of the data-driven model to classify stimulation volumes as 'causing SID' or 'not causing SID' was validated by calculating receiver operating characteristics (ROC) in an independent out-of-sample cohort comprising 14 patients with PD and STN-DBS.

RESULTS

Local fibre-based stimulation maps showed an involvement of fibres running lateral and posteromedial to the STN in the pathogenesis of SID, independent of the investigated hemisphere. ROC analysis in the independent out-of-sample cohort resulted in a good fit of the data-driven model for both hemispheres (area under the curve (AUC)left=0.88, AUCright=0.88).

CONCLUSIONS

This study reveals an involvement of both, cerebello-thalamic fibres, as well as the pyramidal tract, in the pathogenesis of SID in STN-DBS. The results may impact future postoperative programming strategies to avoid SID in patients with PD and STN-DBS TRIAL REGISTRATION NUMBER: DRKS00023221; German Clinical Trials Register (DRKS) Number.

Smartphone Voice Calls Provide Early Biomarkers of Parkinsonism in Rapid Eye Movement Sleep Behavior Disorder

BACKGROUND

Speech dysfunction represents one of the initial motor manifestations to develop in Parkinson's disease (PD) and is measurable through smartphone.

OBJECTIVE

The aim was to develop a fully automated and noise-resistant smartphone-based system that can unobtrusively screen for prodromal parkinsonian speech disorder in subjects with isolated rapid eye movement sleep behavior disorder (iRBD) in a real-world scenario.

METHODS

This cross-sectional study assessed regular, everyday voice call data from individuals with iRBD compared to early PD patients and healthy controls via a developed smartphone application. The participants also performed an active, regular reading of a short passage on their smartphone. Smartphone data were continuously collected for up to 3 months after the standard in-person assessments at the clinic.

RESULTS

A total of 3525 calls that led to 5990 minutes of preprocessed speech were extracted from 72 participants, comprising 21 iRBD patients, 26 PD patients, and 25 controls. With a high area under the curve of 0.85 between iRBD patients and controls, the combination of passive and active smartphone data provided a comparable or even more sensitive evaluation than laboratory examination using a high-quality microphone. The most sensitive features to induce prodromal neurodegeneration in iRBD included imprecise vowel articulation during phone calls (P = 0.03) and monopitch in reading (P = 0.05). Eighteen minutes of speech corresponding to approximately nine calls was sufficient to obtain the best sensitivity for the screening.

CONCLUSION

We consider the developed tool widely applicable to deep longitudinal digital phenotyping data with future applications in neuroprotective trials, deep brain stimulation optimization, neuropsychiatry, speech therapy, population screening, and beyond. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Spike-phase coupling of subthalamic neurons to posterior opercular cortex predicts speech sound accuracy

Speech provides a rich context for understanding how cortical interactions with the basal ganglia contribute to unique human behaviors, but opportunities for direct intracranial recordings across cortical-basal ganglia networks are rare. We recorded electrocorticographic signals in the cortex synchronously with single units in the basal ganglia during awake neurosurgeries where subjects spoke syllable repetitions. We discovered that individual STN neurons have transient (200ms) spike-phase coupling (SPC) events with multiple cortical regions. The spike timing of STN neurons was coordinated with the phase of theta-alpha oscillations in the posterior supramarginal and superior temporal gyrus during speech planning and production. Speech sound errors occurred when this STN-cortical interaction was delayed. Our results suggest that the STN supports mechanisms of speech planning and auditory-sensorimotor integration during speech production that are required to achieve high fidelity of the phonological and articulatory representation of the target phoneme. These findings establish a framework for understanding cortical-basal ganglia interaction in other human behaviors, and additionally indicate that firing-rate based models are insufficient for explaining basal ganglia circuit behavior.

Short-term effects of transcranial direct current stimulation on motor speech in Parkinson's disease: a pilot study

INTRODUCTION

Hypokinetic dysarthria (HD) is a common motor speech symptom of Parkinson's disease (PD) which does not respond well to PD treatments. We investigated short-term effects of transcranial direct current stimulation (tDCS) on HD in PD using acoustic analysis of speech. Based on our previous studies we focused on stimulation of the right superior temporal gyrus (STG) - an auditory feedback area.

METHODS

In 14 PD patients with HD, we applied anodal, cathodal and sham tDCS to the right STG using a cross-over design. A protocol consisting of speech tasks was performed prior to and immediately after each stimulation session. Linear mixed models were used for the evaluation of the effects of each stimulation condition on the relative change of acoustic parameters. We also performed a simulation of the mean electric field induced by tDCS.

RESULTS

Linear mixed model showed a statistically significant effect of the stimulation condition on the relative change of median duration of silences longer than 50 ms (p = 0.015). The relative change after the anodal stimulation (mean = -5.9) was significantly lower as compared to the relative change after the sham stimulation (mean = 12.8), p = 0.014. We also found a correlation between the mean electric field magnitude in the right STG and improvement of articulation precision after anodal tDCS (R = 0.637; p = 0.019).

CONCLUSIONS

The exploratory study showed that anodal tDCS applied over the auditory feedback area may lead to shorter pauses in a speech of PD patients.

A bibliometric analysis of speech and language impairments in Parkinson's disease based on Web of Science

Many individuals with Parkinson's disease suffer from speech and language impairments that significantly impact their quality of life. Despite several studies on these disorders, there is a lack of relevant bibliometric analyses. This paper conducted a bibliometric analysis of 3,610 papers on speech and language impairments in Parkinson's disease patients from January 1961 to November 2023, based on the Web of Science Core Collection database. Using Citespace software, the analysis focused on annual publication volume, cooperation among countries and institutions, author collaborations, journals, co-citation references, and keywords, aiming to explore the current research status, hotspots, and frontiers in this field. The number of annual publications related to speech and language impairment in Parkinson's disease have been increasing over the years. The USA leads in the number of publications. Research hotspots include the mechanism underlying speech and language impairments, clinical symptoms, automated diagnosis and classification of patients with PD using linguistic makers, and rehabilitation interventions.

Machine learning decoding of single neurons in the thalamus for speech brain-machine interfaces

Objective. Our goal is to decode firing patterns of single neurons in the left ventralis intermediate nucleus (Vim) of the thalamus, related to speech production, perception, and imagery. For realistic speech brain-machine interfaces (BMIs), we aim to characterize the amount of thalamic neurons necessary for high accuracy decoding.Approach. We intraoperatively recorded single neuron activity in the left Vim of eight neurosurgical patients undergoing implantation of deep brain stimulator or RF lesioning during production, perception and imagery of the five monophthongal vowel sounds. We utilized the Spade decoder, a machine learning algorithm that dynamically learns specific features of firing patterns and is based on sparse decomposition of the high dimensional feature space.Main results. Spade outperformed all algorithms compared with, for all three aspects of speech: production, perception and imagery, and obtained accuracies of 100%, 96%, and 92%, respectively (chance level: 20%) based on pooling together neurons across all patients. The accuracy was logarithmic in the amount of neurons for all three aspects of speech. Regardless of the amount of units employed, production gained highest accuracies, whereas perception and imagery equated with each other.Significance. Our research renders single neuron activity in the left Vim a promising source of inputs to BMIs for restoration of speech faculties for locked-in patients or patients with anarthria or dysarthria to allow them to communicate again. Our characterization of how many neurons are necessary to achieve a certain decoding accuracy is of utmost importance for planning BMI implantation.

Effects of Deep-Brain Stimulation on Speech: Perceptual and Acoustic Data

PURPOSE

This study examined speech changes induced by deep-brain stimulation (DBS) in speakers with Parkinson's disease (PD) using a set of auditory-perceptual and acoustic measures.

METHOD

Speech recordings from nine speakers with PD and DBS were compared between DBS-On and DBS-Off conditions using auditory-perceptual and acoustic analyses. Auditory-perceptual ratings included voice quality, articulation precision, prosody, speech intelligibility, and listening effort obtained from 44 listeners. Acoustic measures were made for voicing proportion, second formant frequency slope, vowel dispersion, articulation rate, and range of fundamental frequency and intensity.

RESULTS

No significant changes were found between DBS-On and DBS-Off for the five perceptual ratings. Four of six acoustic measures revealed significant differences between the two conditions. While articulation rate and acoustic vowel dispersion increased, voicing proportion and intensity range decreased from the DBS-Off to DBS-On condition. However, a visual examination of the data indicated that the statistical significance was mostly driven by a small number of participants, while the majority did not show a consistent pattern of such changes.

CONCLUSIONS

Our data, in general, indicate no-to-minimal changes in speech production ensued from DBS stimulation. The findings are discussed with a focus on large interspeaker variability in PD in terms of their speech characteristics and the potential effects of DBS on speech.

Mechanisms of Swallowing, Speech and Voice Disorders in Parkinson's Disease: Literature Review with Our First Evidence for the Periperal Nervous System Involvement

The majority of patients with Parkinson's disease (PD) develop swallowing, speech, and voice (SSV) disorders. Importantly, swallowing difficulty or dysphagia and related aspiration are life-threatening conditions for PD patients. Although PD treatments have significant therapeutic effects on limb motor function, their effects on SSV disorders are less impressive. A large gap in our knowledge is that the mechanisms of SSV disorders in PD are poorly understood. PD was long considered to be a central nervous system disorder caused by the death of dopaminergic neurons in the basal ganglia. Aggregates of phosphorylated α-synuclein (PAS) underlie PD pathology. SSV disorders were thought to be caused by the same dopaminergic problem as those causing impaired limb movement; however, there is little evidence to support this. The pharynx, larynx, and tongue play a critical role in performing upper airway (UA) motor tasks and their dysfunction results in disordered SSV. This review aims to provide an overview on the neuromuscular organization patterns, functions of the UA structures, clinical features of SSV disorders, and gaps in knowledge regarding the pathophysiology underlying SSV disorders in PD, and evidence supporting the hypothesis that SSV disorders in PD could be associated, at least in part, with PAS damage to the peripheral nervous system controlling the UA structures. Determining the presence and distribution of PAS lesions in the pharynx, larynx, and tongue will facilitate the identification of peripheral therapeutic targets and set a foundation for the development of new therapies to treat SSV disorders in PD.

Voice analytics in the wild: Validity and predictive accuracy of common audio-recording devices

The use of voice recordings in both research and industry practice has increased dramatically in recent years-from diagnosing a COVID-19 infection based on patients' self-recorded voice samples to predicting customer emotions during a service center call. Crowdsourced audio data collection in participants' natural environment using their own recording device has opened up new avenues for researchers and practitioners to conduct research at scale across a broad range of disciplines. The current research examines whether fundamental properties of the human voice are reliably and validly captured through common consumer-grade audio-recording devices in current medical, behavioral science, business, and computer science research. Specifically, this work provides evidence from a tightly controlled laboratory experiment analyzing 1800 voice samples and subsequent simulations that recording devices with high proximity to a speaker (such as a headset or a lavalier microphone) lead to inflated measures of amplitude compared to a benchmark studio-quality microphone while recording devices with lower proximity to a speaker (such as a laptop or a smartphone in front of the speaker) systematically reduce measures of amplitude and can lead to biased measures of the speaker's true fundamental frequency. We further demonstrate through simulation studies that these differences can lead to biased and ultimately invalid conclusions in, for example, an emotion detection task. Finally, we outline a set of recording guidelines to ensure reliable and valid voice recordings and offer initial evidence for a machine-learning approach to bias correction in the case of distorted speech signals.

Levodopa may modulate specific speech impairment in Parkinson's disease: an fMRI study

Hypokinetic dysarthria (HD) is a difficult-to-treat symptom affecting quality of life in patients with Parkinson's disease (PD). Levodopa may partially alleviate some symptoms of HD in PD, but the neural correlates of these effects are not fully understood. The aim of our study was to identify neural mechanisms by which levodopa affects articulation and prosody in patients with PD. Altogether 20 PD patients participated in a task fMRI study (overt sentence reading). Using a single dose of levodopa after an overnight withdrawal of dopaminergic medication, levodopa-induced BOLD signal changes within the articulatory pathway (in regions of interest; ROIs) were studied. We also correlated levodopa-induced BOLD signal changes with the changes in acoustic parameters of speech. We observed no significant changes in acoustic parameters due to acute levodopa administration. After levodopa administration as compared to the OFF dopaminergic condition, patients showed task-induced BOLD signal decreases in the left ventral thalamus (p = 0.0033). The changes in thalamic activation were associated with changes in pitch variation (R = 0.67, p = 0.006), while the changes in caudate nucleus activation were related to changes in the second formant variability which evaluates precise articulation (R = 0.70, p = 0.003). The results are in line with the notion that levodopa does not have a major impact on HD in PD, but it may induce neural changes within the basal ganglia circuitries that are related to changes in speech prosody and articulation.

Neuronal Encoding of Speech Features in the Human Thalamus in Parkinson's Disease and Essential Tremor Patients

BACKGROUND AND OBJECTIVES

The human thalamus is known, from stimulation studies and functional imaging, to participate in high-level language tasks. The goal of this study is to find whether and how speech features, in particular, vowel phonemes, are encoded in the neuronal activity of the thalamus, and specifically of the left ventralis intermediate nucleus (Vim), during speech production, perception, and imagery.

METHODS

In this cross-sectional study, we intraoperatively recorded single neuron activity in the left Vim of eight neurosurgical patients with Parkinson's disease (PD) (n = 4) or essential tremor (n = 4) undergoing implantation of deep brain stimulation (n = 3) or radiofrequency lesioning (n = 5) while patients articulated the five monophthongal vowel sounds.

RESULTS

In this article, we report that single neurons in the left Vim encode individual vowel phonemes mainly during speech production but also during perception and imagery. They mainly use one of two encoding schemes: broad or sharp tuning, with a similar percentage of units each. Sinusoidal tuning has been demonstrated in almost half of the broadly tuned units. Patients with PD had a lower percentage of speech-related units in each aspect of speech (production, perception, and imagery), a significantly lower percentage of broadly tuned units, and significantly lower median firing rates during speech production and perception, but significantly higher rates during imagery, than patients with essential tremor.

CONCLUSION

The results suggest that the left Vim uses mixed encoding schemes for speech features. Our findings explain, at the single neuron level, why deep brain stimulation and radiofrequency lesioning of the left Vim are likely to cause speech side effects. Moreover, they may indicate that speech-related units in the left Vim of patients with PD may be degraded even in the subclinical phase.

Effects of a Concurrent Working Memory Task on Speech Acoustics in Parkinson's Disease

PURPOSE

The purpose of this study was to determine the effect of a concurrent working memory task on acoustic measures of speech in individuals with Parkinson's disease (PD).

METHOD

Individuals with PD and age- and sex-matched controls performed a speaking task with and without a Stroop-like concurrent working memory task. Cepstral peak prominence, low-to-high spectral energy ratio, fundamental frequency (fo) standard deviation, articulation rate, pause duration, articulatory-acoustic vowel space, relative fo, mean voice onset time (VOT), and VOT variability were calculated for each condition. Mixed-model analyses of variance were performed to determine the effects of group, condition (presence of the concurrent working memory task), and their interaction on the acoustic measures.

RESULTS

All measures except for VOT variability, mean pause duration, and relative fo offset differed between people with and without PD. Cepstral peak prominence, articulation rate, and relative fo offset differed as a function of condition. However, no measures indicated disparate effects of condition as a function of group.

CONCLUSION

Although differentially impactful on limb motor function in PD, here a concurrent working memory task was not found to be differentially disruptive to speech acoustics in PD.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.24759648.

Self-perceived affective, behavioral, and cognitive reactions associated with voice use in people with Parkinson's disease: a pilot study

PURPOSE

This study aimed to compare the affective, behavioral, and cognitive reactions related to vocal function in people with Parkinson's disease (PWPD) and healthy controls using the Behavior Assessment Battery - Voice (BAB-Voice). The test's internal consistency was also described.

METHODS

31 PWPD and 19 healthy controls were recruited from September 2020 to March 2021. Participants completed four BAB-Voice subtests: Speech Situation Checklist - Emotional Reaction (SSC-ER), the Speech Situation Checklist - Speech Disruption (SSC-SD), Behavior Checklist (BCL), and Communication Attitude Test for Adults (BigCAT), describing the experienced negative emotional reaction, voice disruptions, coping behaviors, and negative attitude regarding communication respectively. Subtest scores were calculated and analyzed.

RESULTS

The scores of the PWPD were significantly different from those of the controls (Pillai's Trace = 0.344, F[4] = 5.508, p = .001, ηp2 = .344): PWPD showed more negative emotions and voice problems, more coping behaviors, and more negative speech-related attitude compared to healthy controls. All subtests showed excellent internal consistency.

CONCLUSIONS

The BAB-Voice proved a tool with a good internal consistency that measured different psychosocial reactions in PWPD versus controls. PWPD exhibited significantly more negative emotions and voice problems in specific speech situations, more coping behaviors, and a more negative speech-related attitude. The specificity of information obtained from the BAB-Voice may aid in improving the treatment planning of voice disorders in PWPD.

Computerized analysis of hypomimia and hypokinetic dysarthria for improved diagnosis of Parkinson's disease

Background and Objective

An aging society requires easy-to-use approaches for diagnosis and monitoring of neurodegenerative disorders, such as Parkinson's disease (PD), so that clinicians can effectively adjust a treatment policy and improve patients' quality of life. Current methods of PD diagnosis and monitoring usually require the patients to come to a hospital, where they undergo several neurological and neuropsychological examinations. These examinations are usually time-consuming, expensive, and performed just a few times per year. Hence, this study explores the possibility of fusing computerized analysis of hypomimia and hypokinetic dysarthria (two motor symptoms manifested in the majority of PD patients) with the goal of proposing a new methodology of PD diagnosis that could be easily integrated into mHealth systems.

Methods

We enrolled 73 PD patients and 46 age- and gender-matched healthy controls, who performed several speech/voice tasks while recorded by a microphone and a camera. Acoustic signals were parametrized in the fields of phonation, articulation and prosody. Video recordings of a face were analyzed in terms of facial landmarks movement. Both modalities were consequently modeled by the XGBoost algorithm.

Results

The acoustic analysis enabled diagnosis of PD with 77% balanced accuracy, while in the case of the facial analysis, we observed 81% balanced accuracy. The fusion of both modalities increased the balanced accuracy to 83% (88% sensitivity and 78% specificity). The most informative speech exercise in the multimodality system turned out to be a tongue twister. Additionally, we identified muscle movements that are characteristic of hypomimia.

Conclusions

The introduced methodology, which is based on the myriad of speech exercises likewise audio and video modality, allows for the detection of PD with an accuracy of up to 83%. The speech exercise - tongue twisters occurred to be the most valuable from the clinical point of view. Additionally, the clinical interpretation of the created models is illustrated. The presented computer-supported methodology could serve as an extra tool for neurologists in PD detection and the proposed potential solution of mHealth will facilitate the patient's and doctor's life.

Exploring the Efficacy of the Effortful Swallow Maneuver for Improving Swallowing in People With Parkinson Disease-A Pilot Study

Objectives

To determine the immediate (compensatory) and longer term (rehabilitative) effect of the effortful swallow (ES) maneuver on physiological swallowing parameters in Parkinson disease.

Design

Virtual intervention protocol via Microsoft Teams with pre- and post-videofluoroscopic swallowing studies.

Setting

Outpatient hospital setting, with intervention performed virtually.

Participants

Eight participants (median age 74 years [63-82])with Parkinson disease (years post onset 3-20) with a Hoehn and Yahr scale score between 2 and 4 (N=8).

Interventions

ES maneuver, initiated using a maximum effort isometric tongue-to-palate press, with biofeedback provided using the Iowa Oral Performance Instrument. The protocol included 30 minute sessions twice daily, 5 days/week for 4 weeks.

Main Outcome Measures

Penetration-Aspiration Scale scores, time-to-laryngeal-vestibule-closure, total pharyngeal residue, and pharyngeal area at maximum constriction as seen on lateral view videofluoroscopy.

Results

No consistent, systematic trends were identified in the direction of improvement or deterioration across Penetration-Aspiration Scale scores, time-to-laryngeal-vestibule-closure, pharyngeal area at maximum constriction, or total pharyngeal residue.

Conclusions

Heterogeneous response to the ES as both a compensatory and rehabilitative technique. Positive response on the compensatory probe was predictive of positive response after rehabilitation.

Continuous theta burst stimulation over right cerebellum for speech impairment in Parkinson's disease: study protocol for a randomized, sham-controlled, clinical trial

Background

Speech impairment is a common symptom of Parkinson's disease (PD) that worsens with disease progression and affects communication and quality of life. Current pharmacological and surgical treatments for PD have inconsistent effects on speech impairment. The cerebellum is an essential part of sensorimotor network that regulates speech production and becomes dysfunctional in PD. Continuous theta-burst stimulation (cTBS) is a non-invasive brain stimulation technique that can modulate the cerebellum and its connections with other brain regions.

Objective

To investigate whether cTBS over the right cerebellum coupled with speech-language therapy (SLT) can improve speech impairment in PD.

Methods

In this randomized controlled trial (RCT), 40 patients with PD will be recruited and assigned to either an experimental group (EG) or a control group (CG). Both groups will receive 10 sessions of standard SLT. The EG will receive real cTBS over the right cerebellum, while the CG will receive sham stimulation. Blinded assessors will evaluate the treatment outcome at three time points: pre-intervention, post-intervention, and at a 12-week follow-up. The primary outcome measures are voice/speech quality and neurobehavioral parameters of auditory-vocal integration. The secondary outcome measures are cognitive function, quality of life, and functional connectivity determined by resting-state functional magnetic resonance imaging (fMRI).

Significance

This trial will provide evidence for the efficacy and safety of cerebellar cTBS for the treatment of speech impairment in PD and shed light on the neural mechanism of this intervention. It will also have implications for other speech impairment attributed to cerebellar dysfunctions.

Clinical trial registration

www.chictr.org.cn, identifier ChiCTR2100050543.

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.

Monitoring the Effect of Levodopa Using Sustained Phonemes in Parkinson's Disease Patients

Parkinson's disease (PD) is a neurological disease identified by multiple symptoms, and levodopa is one of the most effective medications for treating the disease. To determine the dosage of levodopa, it is necessary to meet on a regular basis and observe motor function. The early detection and progression of the disease have been proposed using hypokinetic dysarthria. However, previous studies have not examined the effects of levodopa on speech rigorously and have provided inconsistent results. In this study, three sustained phonemes of PD patients were investigated for the effect of medication. A set of features characterizing vocal fold dynamics as well as the vocal tract coordinators were extracted from the sustained phonemes /of 28 PD patients during levodopa medication off and on states. All the features were statistically investigated and classified using a linear discriminant analysis (LDA) classifier. LDA classifier identified medication on from medication off based on the combined features from phoneme /a/, /o/ and /m/ with the accuracy=82.75% and F1-score=82.18%. Voice recording of PD patients during sustained phonemes /a/, /o/ and /m/ has the potential for identifying whether the patients are in On state or Off state of medication.Clinical Relevance- The outcomes of this study have the potential to monitor the effect and progress of levodopa on PD patients.

Reduced syntactic recursion in spontaneous speech of Parkinson's disease patients

Although characterized as a movement disorder, Parkinson's disease (PD) affects more than just the motor system. Within the heterogenous non-motor symptoms, language impairment is frequent but poorly understood beyond semantic processing. This study investigates the impact of PD on syntactic subordination in spontaneous language production. Fifteen PD patients in ON levodopa status narrated a short story guided by a set of pictures. Thirteen PD patients were also assessed in OFF levodopa status. Narrations were digitally recorded, subsequently transcribed and annotated, making the produced speech accessible to systematical quantitative analysis. Compared to a healthy matched control group, PD patients showed a significant reduction of subordinating structures while the number of non-embedding sentences remained unaffected. No significant effect comparing ON versus OFF levodopa status emerged. Our results suggest a contribution of the basal ganglia to language processing, such as syntactic composition, which, however, does not seem to be dopamine dependent.

CNN-Based Identification of Parkinson's Disease from Continuous Speech in Noisy Environments

Parkinson's disease is a progressive neurodegenerative disorder caused by dopaminergic neuron degeneration. Parkinsonian speech impairment is one of the earliest presentations of the disease and, along with tremor, is suitable for pre-diagnosis. It is defined by hypokinetic dysarthria and accounts for respiratory, phonatory, articulatory, and prosodic manifestations. The topic of this article targets artificial-intelligence-based identification of Parkinson's disease from continuous speech recorded in a noisy environment. The novelty of this work is twofold. First, the proposed assessment workflow performed speech analysis on samples of continuous speech. Second, we analyzed and quantified Wiener filter applicability for speech denoising in the context of Parkinsonian speech identification. We argue that the Parkinsonian features of loudness, intonation, phonation, prosody, and articulation are contained in the speech, speech energy, and Mel spectrograms. Thus, the proposed workflow follows a feature-based speech assessment to determine the feature variation ranges, followed by speech classification using convolutional neural networks. We report the best classification accuracies of 96% on speech energy, 93% on speech, and 92% on Mel spectrograms. We conclude that the Wiener filter improves both feature-based analysis and convolutional-neural-network-based classification performances.

Repetitive transcranial magnetic stimulation for hypokinetic dysarthria in Parkinson's disease enhances white matter integrity of the auditory-motor loop

BACKGROUND AND PURPOSE

In our previous study, repeated sessions of repetitive transcranial magnetic stimulation (rTMS) over the auditory feedback area were shown to improve hypokinetic dysarthria (HD) in Parkinson's disease (PD) and led to changes in functional connectivity within the left-sided articulatory networks. We analyzed data from this previous study and assessed the effects of rTMS for HD in PD on the diffusion parameters of the left anterior arcuate fasciculus (AAF), which connects the auditory feedback area with motor regions involved in articulation.

METHODS

Patients were assigned to 10 sessions of real or sham 1-Hz stimulation over the right posterior superior temporal gyrus. Stimulation effects were evaluated using magnetic resonance diffusion tensor imaging and by a speech therapist using a validated tool (Phonetics score of the Dysarthric Profile) at baseline, immediately after 2 weeks of stimulation, and at follow-up visits at Weeks 6 and 10 after the baseline.

RESULTS

Altogether, data from 33 patients were analyzed. A linear mixed model revealed significant time-by-group interaction (p = 0.006) for the relative changes of fractional anisotropy of the AAF; the value increases were associated with the temporal evolution of the Phonetics score (R = 0.367, p = 0.028) in the real stimulation group.

CONCLUSIONS

Real rTMS treatment for HD in PD as compared to sham stimulation led to increases of white matter integrity of the auditory-motor loop during the 2-month follow-up period. The changes were related to motor speech improvements.

Early detection of Parkinson disease using stacking ensemble method

Parkinson's disease (PD) is a common progressive neurodegenerative disorder that occurs due to corrosion of the substantianigra, located in the thalamic region of the human brain, and is responsible for the transmission of neural signals throughout the human body using brain chemical, termed as "dopamine." Diagnosis of PD is difficult, as it is often affected by the characteristics of the medical data of the patients, which include the presence of various indicators, imbalance cases of patients' data records, similar cases of healthy/affected persons, etc. Hence, sometimes the process of diagnosis may also be affected by human error. To overcome this problem some intelligent models have been proposed; however, most of them are single classifier-based models and due to this these models cannot handle noisy and imbalanced data properly and thus sometimes overfit the model. To reduce bias and variance, and to avoid overfitting of a single classifier-based model, this paper proposes an ensemble-based PD diagnosis model, named Ensembled Expert System for Diagnosis of Parkinson's Disease (EESDPD) with relevant features and a simple stacking ensemble technique. The proposed EESDPD aggregates diverse assumptions for making the prediction. The performance of the proposed EESDPD is compared with the performances of logistic regression, SVM, Naïve Bayes, Random Forest, XGBoost, simple Decision Tree, B-TDS-PD and B-TESM-PD in terms of classification accuracy, precision, recall and F1-score measures.

The Effects of Deep Brain Stimulation on Speech Motor Control in People With Parkinson's Disease

PURPOSE

Despite the overall benefits of deep brain stimulation (DBS) in Parkinson's disease (PD), its effects on speech production have been mixed when examined using auditory-perceptual and acoustic measures. This study investigated the effects of DBS on the lip and jaw kinematics during sentence production in individuals with dysarthria secondary to PD.

METHOD

Twenty-seven participants from three groups were included in the study: (a) individuals with PD and without DBS (PD group), (b) individuals with PD and with DBS (PD-DBS group), and (c) neurologically healthy control speakers (HC group). Lip and jaw movements during speech were recorded using optical motion capture and analyzed for path distance, speed, duration, articulatory stability, and interarticulator coordination.

RESULTS

The PD-DBS group showed (a) increased path distance compared with the PD and HC groups and (b) increased speed compared with the PD group but not the HC group. Both PD and PD-DBS groups exhibited lengthened sentence duration compared with the HC group. Articulatory stability was greater for the two PD groups, PD and PD-DBS, compared with the HC group. Spatial, but not temporal, coordination was lower for the PD group than for the other two groups. The only kinematic changes between the DBS on and off conditions within the PD-DBS group were increases in spatial coordination.

CONCLUSIONS

These data suggest that DBS primarily affects the amplitude scaling of articulatory movements, but not the temporal scaling, in individuals with PD. The findings are discussed with respect to the DBS-induced neural changes and their effects on speech motor control in PD.

Deep Brain Stimulation Impact on Voice and Speech Quality in Parkinson's Disease: A Systematic Review

OBJECTIVE

Deep brain stimulation (DBS) has considerable efficacy for the motor dysfunction of idiopathic Parkinson's disease (PD) on patient quality of life. However, the benefit of DBS on voice and speech quality remains controversial. We carried out a systematic review to understand the influence of DBS on parkinsonian dysphonia and dysarthria.

DATA SOURCES

A PubMed/MEDLINE and Cochrane systematic review was carried out following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) and Population, Intervention, Comparison, Outcome, Timing, and Setting (PICOTS) statements.

REVIEW METHODS

Three investigators screened studies published in the literature from inception to May 2022. The following data were retrieved: age, demographic, sex, disease duration, DBS duration, DBS location, speech, and voice quality measurements.

RESULTS

From the 180 studies identified, 44 publications met the inclusion criteria, accounting for 866 patients. Twenty-nine studies focused on voice/speech quality in subthalamic DBS patients, and 6 included patients with stimulation of pallidal, thalamic, and zona incerta regions. Most studies (4/6) reported a deterioration of the vocal parameters on subjective voice quality evaluation. For speech, the findings were more contrasted. There was an important heterogeneity between studies regarding the voice and speech quality outcomes used to evaluate the impact of DBS on voice/speech quality.

CONCLUSION

The impact of DBS on voice and speech quality significantly varies between studies. The stimulated anatomical region may have a significant role since the stimulation of the pallidal area was mainly associated with voice quality improvement, in contrast with other regions. Future controlled studies comparing all region stimulation are needed to get reliable findings.

LEVEL OF EVIDENCE

Level III: evidence from evidence summaries developed from systematic reviews.

Effects of intensive speech treatment on Mandarin speakers with Parkinson's Disease: A review

BACKGROUND

Benefits of intensive speech treatment have been documented for a range of speech signs in English speakers with Parkinson's Disease (PD). However, the answer to a critical question that whether the same treatment benefits speech variables including intelligibility in Mandarin speakers is still unclear. In order to develop a targeted speech treatment for Mandarin speakers with PD, we reviewed the efficacy of intensive speech treatment to improve vocal loudness and functional communication and discuss possible explanations for efficacy on Mandarin speakers with PD.

METHODS

Literatures about intensive speech treatment for Mandarin speakers with PD were retrieved from PubMed, Web of Science, Embase, China National Knowledge Infrastructure (CNKI), Wanfang and Weipu Database for Chinese Technical Periodicals (VIP) Database. Search strategy was (voice therapy OR speech therapy OR voice treatment OR speech treatment OR voice training OR speech training OR voice rehabilitation OR speech rehabilitation OR Lee Silverman voice treatment OR intensive speech treatment) and (Parkinson's disease) and (Mandarin speakers OR Chinese OR Chinese people).

RESULTS

Five randomized controlled trials were selected and possible explanations for efficacy on individuals with PD are discussed. Further research directions are suggested.

CONCLUSION

The existing evidence from treatment efficacy studies of intensive speech treatment provides support for improving vocal loudness, speech intelligibility, pitch and rate in Mandarin speakers with PD. Our future research will continue to work to conduct a large sample multicenter randomized controlled trial to provide high quality evidence and understand the basic mechanisms accompanying treatment-related change.

Results of a Randomized Clinical Trial of Speech After Early Neurostimulation in Parkinson's Disease

BACKGROUND

The EARLYSTIM trial demonstrated for Parkinson's disease patients with early motor complications that deep brain stimulation of the subthalamic nucleus (STN-DBS) and best medical treatment (BMT) was superior to BMT alone.

OBJECTIVE

This prospective, ancillary study on EARLYSTIM compared changes in blinded speech intelligibility assessment between STN-DBS and BMT over 2 years, and secondary outcomes included non-speech oral movements (maximum phonation time [MPT], oral diadochokinesis), physician- and patient-reported assessments.

METHODS

STN-DBS (n = 102) and BMT (n = 99) groups underwent assessments on/off medication at baseline and 24 months (in four conditions: on/off medication, ON/OFF stimulation-for STN-DBS). Words and sentences were randomly presented to blinded listeners, and speech intelligibility rate was measured. Statistical analyses compared changes between the STN-DBS and BMT groups from baseline to 24 months.

RESULTS

Over the 2-year period, changes in speech intelligibility and MPT, as well as patient-reported outcomes, were not different between groups, either off or on medication or OFF or ON stimulation, but most outcomes showed a nonsignificant trend toward worsening in both groups. Change in oral diadochokinesis was significantly different between STN-DBS and BMT groups, on medication and OFF STN-DBS, with patients in the STN-DBS group performing slightly worse than patients under BMT only. A signal for clinical worsening with STN-DBS was found for the individual speech item of the Unified Parkinson's Disease Rating Scale, Part III.

CONCLUSION

At this early stage of the patients' disease, STN-DBS did not result in a consistent deterioration in blinded speech intelligibility assessment and patient-reported communication, as observed in studies of advanced Parkinson's Disease. © 2022 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Is Disrupted Mitophagy a Central Player to Parkinson's Disease Pathology?

Whilst the pathophysiology at a cellular level has been defined, the cause of Parkinson's disease (PD) remains poorly understood. This neurodegenerative disorder is associated with impaired dopamine transmission in the substantia nigra, and protein accumulations known as Lewy bodies are visible in affected neurons. Cell culture models of PD have indicated impaired mitochondrial function, so the focus of this paper is on the quality control processes involved in and around mitochondria. Mitochondrial autophagy (mitophagy) is the process through which defective mitochondria are removed from the cell by internalisation into autophagosomes which fuse with a lysosome. This process involves many proteins, notably including PINK1 and parkin, both of which are known to be coded on genes associated with PD. Normally in healthy individuals, PINK1 associates with the outer mitochondrial membrane, which then recruits parkin, activating it to attach ubiquitin proteins to the mitochondrial membrane. PINK1, parkin, and ubiquitin cooperate to form a positive feedback system which accelerates the deposition of ubiquitin on dysfunctional mitochondria, resulting in mitophagy. However, in hereditary PD, the genes encoding PINK1 and parkin are mutated, resulting in proteins that are less efficient at removing poorly performing mitochondria, leaving cells more vulnerable to oxidative stress and ubiquitinated inclusion bodies, such as Lewy bodies. Current research that looks into the connection between mitophagy and PD is promising, already yielding potentially therapeutic compounds; until now, pharmacological support for the mitophagy process has not been part of the therapeutic arsenal. Continued research in this area is warranted.

Laterality in Parkinson's disease: A neuropsychological review

Laterality of motor symptom onset in Parkinson's disease is both well-known and under-appreciated. Treatment of disorders that have asymmetric pathological features, such as stroke and epilepsy, demonstrate the importance of incorporating hemispheric lateralization and specialization into therapy and care planning. These practices could theoretically extend to Parkinson's disease, providing increased diagnostic accuracy and improved treatment outcomes. Additionally, while motor symptoms have generally received the majority of attention, non-motor features (e.g., autonomic dysfunction) also decrease quality of life and are influenced by asymmetrical neurodegeneration. Due to the laterality of cognitive and behavioral processes in the two brain hemispheres, analysis of hemibody side of onset can potentially give insight into expected symptom profile of the patient and allow for increased predictive accuracy of disease progression and outcome, thus opening the door to personalized and improved therapy in treating Parkinson's disease patients. This review discusses motor and non-motor symptoms (namely autonomic, sensory, emotional, and cognitive dysfunction) of Parkinson's disease in respect to hemispheric lateralization from a theoretical perspective in hopes of providing a framework for future research and personalized treatment.

Exploring factors that influence HRQoL for people living with Parkinson's in one region of Ireland: A cross-sectional study

BACKGROUND

The diversity of symptoms associated with Parkinson's and their impact on functioning have led to an increased interest in exploring factors that impact Health-Related Quality of Life (HRQoL). Although the experience of Parkinson's is unique, some symptoms have a greater impact than others, e.g. depression. Moreover, as the risk of Parkinson's increases with age, the financial and public health impact of this condition is likely to increase, particularly within the context of a globally ageing population. In Ireland, research is ongoing in the pursuit of causes and effective treatments for Parkinson's; however, its impact on everyday living, functioning, and HRQoL is largely under-examined. This study aims to describe factors that influence HRQoL for people with Parkinson's (PwP) in one region of Ireland.

METHODS

A cross-sectional postal survey was conducted among people living with Parkinson's (n = 208) in one area of Ireland. This survey included socio-demographic questions, Nonmotor Symptoms Questionnaire for Parkinson's disease (NMSQuest), the Geriatric Depression Scale (GDS-15), and the Parkinson's disease Questionnaire (PDQ-39). Statistical analysis was conducted using SPSS, IBM version 25 (SPSS Inc., Chicago, II, USA).

RESULTS

Participants reflected a predominantly older population who were married, and lived in their own homes (91%). Participants diagnosed the longest reported poorer HRQoL regarding mobility, activities of daily living, emotional well-being, social support, cognition, communication domains and overall HRQoL. Lower HRQoL correlated with higher depression scores p < 0.001 and participants in the lower HRQoL cohort experienced 2.25 times more non-motor symptoms (NMSs) than participants with higher HRQoL. Hierarchical multiple linear regression analysis predicted Geriatric Depression Scale (GDS15) score, NMS burden, and years since diagnosis to negatively impact HRQoL. Principal component analysis (PCA) also indicated that for the population in this study, components measuring 1) independence/dependence 2) stigma 3) emotional well-being, and 4) pain were central to explaining core aspects of participants' HRQoL.

CONCLUSIONS

Findings highlighted the negative impact of longer disease duration, NMS burden, depression, mobility impairments, and perceived dependence on HRQoL for PwP. The positive influence of perceived independence, social engagement along with close supportive relationships were also identified as key components determining HRQoL. Findings emphasised the importance of long-term healthcare commitment to sustaining social and community supports and therapeutic, rehabilitative initiatives to augment HRQoL for PwP.

Computerized analysis of speech and voice for Parkinson's disease: A systematic review

BACKGROUND AND OBJECTIVE

Speech impairment is an early symptom of Parkinson's disease (PD). This study has summarized the literature related to speech and voice in detecting PD and assessing its severity.

METHODS

A systematic review of the literature from 2010 to 2021 to investigate analysis methods and signal features. The keywords "Automatic analysis" in conjunction with "PD speech" or "PD voice" were used, and the PubMed and ScienceDirect databases were searched. A total of 838 papers were found on the first run, of which 189 were selected. One hundred and forty-seven were found to be suitable for the review. The different datasets, recording protocols, signal analysis methods and features that were reported are listed. Values of the features that separate PD patients from healthy controls were tabulated. Finally, the barriers that limit the wide use of computerized speech analysis are discussed.

RESULTS

Speech and voice may be valuable markers for PD. However, large differences between the datasets make it difficult to compare different studies. In addition, speech analytic methods that are not informed by physiological understanding may alienate clinicians.

CONCLUSIONS

The potential usefulness of speech and voice for the detection and assessment of PD is confirmed by evidence from the classification and correlation results.

On the Relationship between Speech Intelligibility and Fluency Indicators among English-Speaking Individuals with Parkinson’s Diseases

The purpose of the study is to investigate how much of variance in Parkinson's Disease (PD) individuals' speech intelligibility could be predicted by seven speech fluency indicators (i.e., repetition, omission, distortion, correction, unfilled pauses, filled pauses, and speaking rate). Speech data were retrieved from a database containing a reading task produced by a group of 16 English-speaking individuals with PD (Jaeger, Trivedi & Stadtchnitzer, 2019). The results from a multiple regression indicated that an addition of 54% of variance in the speech intelligibility scores among individuals with PD could be accounted for after the speakers' PD severity level measured based on Hoehn and Yahr's (1967) disease stage was included as a covariate. In addition, omission and correction were the two fluency indicators that contributed to the general intelligibility score in a statistically significant way. Specifically, for every one-unit gain in the number of correction and omission, speech intelligibility scores would decline by 0.687 and 0.131 point (out of a 7-point scale), respectively. The current study hence supported Magee, Copland, and Vogel's (2019) view that the language production abilities and quantified dysarthria measures among individuals with PD should be explored together. Additionally, the clinical implications based on the current findings were discussed.

COVID-19: respiratory disease diagnosis with regularized deep convolutional neural network using human respiratory sounds

Human respiratory sound auscultation (HRSA) parameters have been the real choice for detecting human respiratory diseases in the last few years. It is a challenging task to extract the respiratory sound features from the breath, voice, and cough sounds. The existing methods failed to extract the sound features to diagnose respiratory diseases. We proposed and evaluated a new regularized deep convolutional neural network (RDCNN) architecture to accept COVID-19 sound data and essential sound features. The proposed architecture is trained with the COVID-19 sound data sets and gives a better learning curve than any other state-of-the-art model. We examine the performance of RDCNN with Max-Pooling (Model-1) and without Max-Pooling (Model-2) functions. In this work, we observed that RDCNN model performance with three sound feature extraction methods [Soft-Mel frequency channel, Log-Mel frequency spectrum, and Modified Mel-frequency Cepstral Coefficient (MMFCC) spectrum] for COVID-19 sound data sets (KDD-data, ComParE2021-CCS-CSS-Data, and NeurlPs2021-data). To amplify the models' performance, we applied the augmentation technique along with regularization. We have also carried out this work to estimate the mutation of SARS-CoV-2 in the five waves using prognostic models (fractal-based). The proposed model achieves state-of-the-art performance on the COVID-19 sound data set to identify COVID-19 disease symptoms. The model's learnable parameter gradients have vanished in the intermediate layers while optimizing the prediction error which is addressed with our proposed RDCNN model. Our experiments suggested that 3 × 3 kernel size for regularized deep CNN (without max-pooling) shows 2-3% better classification accuracy compared to RDCNN with max-pooling. The experimental results suggest that this new approach may achieve the finest results on respiratory diseases.

Comparison of CNN-Learned vs. Handcrafted Features for Detection of Parkinson's Disease Dysgraphia in a Multilingual Dataset

Parkinson's disease dysgraphia (PDYS), one of the earliest signs of Parkinson's disease (PD), has been researched as a promising biomarker of PD and as the target of a noninvasive and inexpensive approach to monitoring the progress of the disease. However, although several approaches to supportive PDYS diagnosis have been proposed (mainly based on handcrafted features (HF) extracted from online handwriting or the utilization of deep neural networks), it remains unclear which approach provides the highest discrimination power and how these approaches can be transferred between different datasets and languages. This study aims to compare classification performance based on two types of features: features automatically extracted by a pretrained convolutional neural network (CNN) and HF designed by human experts. Both approaches are evaluated on a multilingual dataset collected from 143 PD patients and 151 healthy controls in the Czech Republic, United States, Colombia, and Hungary. The subjects performed the spiral drawing task (SDT; a language-independent task) and the sentence writing task (SWT; a language-dependent task). Models based on logistic regression and gradient boosting were trained in several scenarios, specifically single language (SL), leave one language out (LOLO), and all languages combined (ALC). We found that the HF slightly outperformed the CNN-extracted features in all considered evaluation scenarios for the SWT. In detail, the following balanced accuracy (BACC) scores were achieved: SL—0.65 (HF), 0.58 (CNN); LOLO—0.65 (HF), 0.57 (CNN); and ALC—0.69 (HF), 0.66 (CNN). However, in the case of the SDT, features extracted by a CNN provided competitive results: SL—0.66 (HF), 0.62 (CNN); LOLO—0.56 (HF), 0.54 (CNN); and ALC—0.60 (HF), 0.60 (CNN). In summary, regarding the SWT, the HF outperformed the CNN-extracted features over 6% (mean BACC of 0.66 for HF, and 0.60 for CNN). In the case of the SDT, both feature sets provided almost identical classification performance (mean BACC of 0.60 for HF, and 0.58 for CNN).

Characterization of Mild and Moderate Dysarthria in Parkinson's Disease: Behavioral Measures and Neural Correlates

Purpose

Alterations in speech and voice are among the most common symptoms in Parkinson's disease (PD), often resulting in motor speech disorders such as hypokinetic dysarthria. We investigated dysarthria, verbal fluency, executive functions, and global cognitive function in relation to structural and resting-state brain changes in people with PD.

Methods

Participants with mild-moderate PD (n = 83) were recruited within a randomized controlled trial and divided into groups with varying degrees of dysarthria: no dysarthria (noDPD), mild dysarthria (mildDPD), moderate dysarthria (modDPD), and also combined mildDPD and modDPD into one group (totDPD). Voice sound level and dysphonia, verbal fluency, motor symptoms, executive functions, disease severity, global cognition, and neuroimaging were compared between groups. Gray matter volume and intensity of spontaneous brain activity were analyzed. Additionally, regressions between behavioral and neuroimaging data were performed.

Results

The groups differed significantly in mean voice sound level, dysphonia, and motor symptom severity. Comparing different severity levels of dysarthria to noDPD, groups differed focally in resting-state activity, but not in brain structure. In totDPD, lower scores on semantic verbal fluency, a composite score of executive functions, and global cognition correlated with lower superior temporal gyrus volume.

Conclusion

This study shows that severity of dysarthria may be related to underlying structural and resting-state brain alterations in PD as well as behavioral changes. Further, the superior temporal gyrus may play an important role in executive functions, language, and global cognition in people with PD and dysarthria.

QUCoughScope: An Intelligent Application to Detect COVID-19 Patients Using Cough and Breath Sounds

Problem-Since the outbreak of the COVID-19 pandemic, mass testing has become essential to reduce the spread of the virus. Several recent studies suggest that a significant number of COVID-19 patients display no physical symptoms whatsoever. Therefore, it is unlikely that these patients will undergo COVID-19 testing, which increases their chances of unintentionally spreading the virus. Currently, the primary diagnostic tool to detect COVID-19 is a reverse-transcription polymerase chain reaction (RT-PCR) test from the respiratory specimens of the suspected patient, which is invasive and a resource-dependent technique. It is evident from recent researches that asymptomatic COVID-19 patients cough and breathe in a different way than healthy people. Aim-This paper aims to use a novel machine learning approach to detect COVID-19 (symptomatic and asymptomatic) patients from the convenience of their homes so that they do not overburden the healthcare system and also do not spread the virus unknowingly by continuously monitoring themselves. Method-A Cambridge University research group shared such a dataset of cough and breath sound samples from 582 healthy and 141 COVID-19 patients. Among the COVID-19 patients, 87 were asymptomatic while 54 were symptomatic (had a dry or wet cough). In addition to the available dataset, the proposed work deployed a real-time deep learning-based backend server with a web application to crowdsource cough and breath datasets and also screen for COVID-19 infection from the comfort of the user's home. The collected dataset includes data from 245 healthy individuals and 78 asymptomatic and 18 symptomatic COVID-19 patients. Users can simply use the application from any web browser without installation and enter their symptoms, record audio clips of their cough and breath sounds, and upload the data anonymously. Two different pipelines for screening were developed based on the symptoms reported by the users: asymptomatic and symptomatic. An innovative and novel stacking CNN model was developed using three base learners from of eight state-of-the-art deep learning CNN algorithms. The stacking CNN model is based on a logistic regression classifier meta-learner that uses the spectrograms generated from the breath and cough sounds of symptomatic and asymptomatic patients as input using the combined (Cambridge and collected) dataset. Results-The stacking model outperformed the other eight CNN networks with the best classification performance for binary classification using cough sound spectrogram images. The accuracy, sensitivity, and specificity for symptomatic and asymptomatic patients were 96.5%, 96.42%, and 95.47% and 98.85%, 97.01%, and 99.6%, respectively. For breath sound spectrogram images, the metrics for binary classification of symptomatic and asymptomatic patients were 91.03%, 88.9%, and 91.5% and 80.01%, 72.04%, and 82.67%, respectively. Conclusion-The web-application QUCoughScope records coughing and breathing sounds, converts them to a spectrogram, and applies the best-performing machine learning model to classify the COVID-19 patients and healthy subjects. The result is then reported back to the test user in the application interface. Therefore, this novel system can be used by patients in their premises as a pre-screening method to aid COVID-19 diagnosis by prioritizing the patients for RT-PCR testing and thereby reducing the risk of spreading of the disease.

An Analytical Study of Speech Pathology Detection Based on MFCC and Deep Neural Networks

Diseases of internal organs other than the vocal folds can also affect a person's voice. As a result, voice problems are on the rise, even though they are frequently overlooked. According to a recent study, voice pathology detection systems can successfully help the assessment of voice abnormalities and enable the early diagnosis of voice pathology. For instance, in the early identification and diagnosis of voice problems, the automatic system for distinguishing healthy and diseased voices has gotten much attention. As a result, artificial intelligence-assisted voice analysis brings up new possibilities in healthcare. The work was aimed at assessing the utility of several automatic speech signal analysis methods for diagnosing voice disorders and suggesting a strategy for classifying healthy and diseased voices. The proposed framework integrates the efficacy of three voice characteristics: chroma, mel spectrogram, and mel frequency cepstral coefficient (MFCC). We also designed a deep neural network (DNN) capable of learning from the retrieved data and producing a highly accurate voice-based disease prediction model. The study describes a series of studies using the Saarbruecken Voice Database (SVD) to detect abnormal voices. The model was developed and tested using the vowels /a/, /i/, and /u/ pronounced in high, low, and average pitches. We also maintained the "continuous sentence" audio files collected from SVD to select how well the developed model generalizes to completely new data. The highest accuracy achieved was 77.49%, superior to prior attempts in the same domain. Additionally, the model attains an accuracy of 88.01% by integrating speaker gender information. The designed model trained on selected diseases can also obtain a maximum accuracy of 96.77% (cordectomy × healthy). As a result, the suggested framework is the best fit for the healthcare industry.

How expertise and language familiarity influence perception of speech of people with Parkinson's disease

Parkinson's disease (PD) is a progressive neurological disorder characterized by several motor and non-motor manifestations. PD frequently leads to hypokinetic dysarthria, which affects speech production and often has a detrimental impact on everyday communication. Among the typical manifestations of hypokinetic dysarthria, speech and language therapists (SLTs) identify prosody as the most affected cluster of speech characteristics. However, less is known about how untrained listeners perceive PD speech and how affected prosody influences their assessments of speech. This study explores the perception of sentence type intonation and healthiness of PD speech by listeners with different levels of familiarity with speech disorders in Dutch. We investigated assessments and classification accuracy differences between Dutch-speaking SLTs (n = 18) and Dutch/non-Dutch speaking untrained listeners (n = 27 and n = 124, respectively). We collected speech data from 30 Dutch speakers diagnosed with PD and 30 Dutch healthy controls. The stimuli set consisted of short phrases from spontaneous and read speech and of phrases produced with different sentence type intonation. Listeners participated in an online experiment targeting classification of sentence type intonation and perceived healthiness of speech. Results indicate that both familiarity with speech disorders and with speakers' language are significant and have different effects depending on the task type, as different listener groups demonstrate different classification accuracy. There is evidence that untrained Dutch listeners classify PD speech as unhealthy more accurately than both trained Dutch and untrained non-Dutch listeners, while trained Dutch listeners outperform the other two groups in sentence type classification.

Manipulation of vocal communication and anxiety through pharmacologic modulation of norepinephrine in the Pink1-/- rat model of Parkinson disease

Vocal deficits and anxiety are common, co-occurring, and interacting signs of Parkinson Disease (PD) that have a devastating impact on quality of life. Both manifest early in the disease process. Unlike hallmark motor signs of PD, neither respond adequately to dopamine replacement therapies, suggesting that their disease-specific mechanisms are at least partially extra-dopaminergic. Because noradrenergic dysfunction is also a defining feature of PD, especially early in the disease progression, drug therapies targeting norepinephrine are being trialed for treatment of motor and non-motor impairments in PD. Research assessing the effects of noradrenergic manipulation on anxiety and vocal impairment in PD, however, is sparse. In this pre-clinical study, we quantified the influence of pharmacologic manipulation of norepinephrine on vocal impairment and anxiety in Pink1-/- rats, a translational model of PD that demonstrates both vocal deficits and anxiety. Ultrasonic vocalization acoustics, anxiety behavior, and limb motor activity were tested twice for each rat: after injection of saline and after one of three drugs. We hypothesized that norepinephrine reuptake inhibitors (atomoxetine and reboxetine) and a β receptor antagonist (propranolol) would decrease vocal impairment and anxiety compared to saline, without affecting spontaneous motor activity. Our results demonstrated that atomoxetine and reboxetine decreased anxiety behavior. Atomoxetine also modulated ultrasonic vocalization acoustics, including an increase in vocal intensity, which is almost always reduced in animal models and patients with PD. Propranolol did not affect anxiety or vocalization. Drug condition did not influence spontaneous motor activity. These studies demonstrate relationships among vocal impairment, anxiety, and noradrenergic systems in the Pink1-/- rat model of PD.

Automatic diagnosis of COVID-19 disease using deep convolutional neural network with multi-feature channel from respiratory sound data: Cough, voice, and breath

The problem of respiratory sound classification has received good attention from the clinical scientists and medical researcher’s community in the last year to the diagnosis of COVID-19 disease. The Artificial Intelligence (AI) based models deployed into the real-world to identify the COVID-19 disease from human-generated sounds such as voice/speech, dry cough, and breath. The CNN (Convolutional Neural Network) is used to solve many real-world problems with Artificial Intelligence (AI) based machines. We have proposed and implemented a multi-channeled Deep Convolutional Neural Network (DCNN) for automatic diagnosis of COVID-19 disease from human respiratory sounds like a voice, dry cough, and breath, and it will give better accuracy and performance than previous models. We have applied multi-feature channels such as the data De-noising Auto Encoder (DAE) technique, GFCC (Gamma-tone Frequency Cepstral Coefficients), and IMFCC (Improved Multi-frequency Cepstral Coefficients) methods on augmented data to extract the deep features for the input of the CNN. The proposed approach improves system performance to the diagnosis of COVID-19 disease and provides better results on the COVID-19 respiratory sound dataset.

COVID-19 disease diagnosis with light-weight CNN using modified MFCC and enhanced GFCC from human respiratory sounds

In the last 2 years, medical researchers and clinical scientists have paid close attention to the problem of respiratory sound classification to classify COVID-19 disease symptoms. In the physical world, very few AI-based (Artificial Intelligence) techniques are often used to detect COVID-19/SARS-CoV-2 respiratory disease symptoms from the human respiratory system-generated acoustic sounds such as acoustic voice sound, breathing (inhale and exhale) sounds, and cough sound. We propose a light-weight Convolutional Neural Network (CNN) with Modified-Mel-frequency Cepstral Coefficient (M-MFCC) using different depths and kernel sizes to classify COVID-19 and other respiratory sound disease symptoms such as Asthma, Pertussis, and Bronchitis. The proposed network outperforms conventional feature extraction models and existing Deep Learning (DL) models for COVID-19/SARS-CoV-2 classification accuracy in the range of 4-10%. The model's performance is compared with the COVID-19 crowdsourced benchmark dataset and gives a competitive performance. We applied different receptive fields and depths in the proposed model to get different contextual information that should aid in classification. And our experiments suggested 1 × 12 receptive fields and a depth of 5-Layer for the light-weight CNN to extract and identify the features from respiratory sound data. The model is also trained and tested with different modalities of data to showcase its effectiveness in classification.

Evaluating a Speech-Specific and a Computerized Step-Training-Specific Rhythmic Intervention in Parkinson's Disease: A Cross-Over, Multi-Arms Parallel Study

Background:

Recent studies suggest movements of speech and gait in patients with Parkinson's Disease (PD) are impaired by a common underlying rhythmic dysfunction. If this being the case, motor deficits in speech and gait should equally benefit from rhythmic interventions regardless of whether it is a speech-specific or step-training-specific approach.

Objective:

In this intervention trial, we studied the effects of two rhythmic interventions on speech and gait. These rhythmic intervention programs are similar in terms of intensity and frequency (i.e., 3x per week, 45 min-long sessions for 4 weeks in total), but differ regarding therapeutic approach (rhythmic speech vs. rhythmic balance-mobility training).

Methods:

This study is a cross-over, parallel multi-arms, single blind intervention trial, in which PD patients treated with rhythmic speech-language therapy (rSLT; N = 16), rhythmic balance-mobility training (rBMT; N = 10), or no therapy (NT; N = 18) were compared to healthy controls (HC; N = 17; matched by age, sex, and education: p > 0.82). Velocity and cadence in speech and gait were evaluated at baseline (BL), 4 weeks (4W-T1), and 6 months (6M-T2) and correlated.

Results:

Parameters in speech and gait (i.e., speaking and walking velocity, as well as speech rhythm with gait cadence) were positively correlated across groups (p < 0.01). Statistical analyses involved repeated measures ANOVA across groups and time, as well as independent and one-samples t-tests for within groups analyses. Statistical analyses were amplified using Reliable Change (RC) and Reliable Change Indexes (RCI) to calculate true clinically significant changes due to the treatment on a patient individual level. Rhythmic intervention groups improved across variables and time (total Mean Difference: 3.07 [SD 1.8]; 95% CI 0.2–11.36]) compared to the NT group, whose performance declined significantly at 6 months (p < 0.01). HC outperformed rBMT and NT groups across variables and time (p < 0.001); the rSLT performed similarly to HC at 4 weeks and 6 months in speech rhythm and respiration.

Conclusions:

Speech and gait deficits in PD may share a common mechanism in the underlying cortical circuits. Further, rSLT was more beneficial to dysrhythmic PD patients than rBMT, likely because of the nature of the rhythmic cue.

Partner perception of affective, behavioral, and cognitive reactions to voice use in people with Parkinson’s disease

•

Behavior Assessment Battery – Voice in people with Parkinson’s disease and proxies.

•

Proxies and people with Parkinson’s Disease rate psychosocial impact similarly.

•

Proxies can be part of vocal assessment and treatment in Parkinson’s Disease.

Introduction

People with Parkinson’s disease (PWPD) experience negative feelings, thoughts, and coping behaviors due to the experienced communication challenges. This study aimed to compare the perceptions of PWPD with those of proxies for the affective, behavioral, and cognitive reactions specific to voice production during communicative interactions.

Methods

The Behavior Assessment Battery – Voice (BAB-Voice) was administered to 31 PWPD and their close communication partner/proxy. The BAB-Voice contained four subtests: Speech Situation Checklist – Emotional Reaction (SSC-ER), Speech Situation Checklist – Speech Disruption (SSC-SD), Behavior Checklist (BCL), and Communication Attitude Test for Adults (BigCAT). The scores for each of these subtests were calculated and statistically analyzed.

Results

A repeated measures MANOVA did not find statistically significant differences between the subscores of PWPD and proxies (Pillai’s trace = 0.25, F[4] = 2.22, p =.094, η_p² = 0.25). Fair to excellent agreement between the PWPD and proxies was found. The highest agreement was found on the BigCAT (ICC = 0.80). The SSC-SD (ICC = 0.77) and SSC-ER (ICC = 0.71) still showed excellent agreement, while only fair agreement was found for the BCL (ICC = 0.57).

Conclusion

Proxies were able to identify the affective, behavioral, and cognitive reactions to voice use in PWPD. Communication partners close to the PWPD could, therefore, provide valuable information regarding the assessment and treatment of hypophonia in PD.

Validation of cepstral peak prominence in assessing early voice changes of Parkinson's disease: Effect of speaking task and ambient noise

Although the cepstral peak prominence (CPP) and its variant, the cepstral peak prominence smooth (CPPS), are considered to be robust acoustic measures for the evaluation of dysphonia, whether they are sensitive to capture early voice changes in Parkinson's disease (PD) has not yet been explored. This study aimed to investigate the voice changes via the CPP measures in the idiopathic rapid eye movement sleep behavior disorder (iRBD), a special case of prodromal neurodegeneration, and recently diagnosed and advanced-stage Parkinson's disease (AS-PD) patients using different speaking tasks across noise-free and noisy environments. The sustained vowel phonation, reading of passages, and monologues of 60 early stage untreated PD, 30 advanced-stage Parkinson's disease, 60 iRBD, and 60 healthy control (HC) participants were evaluated. Significant differences were found between the PD groups and controls in sustained phonation via the CPP (p < 0.05) and CPPS (p < 0.01) and the monologue via the CPP (p < 0.01), although neither the CPP nor CPPS measures were sufficiently sensitive to capture the possible prodromal dysphonia in the iRBD. The quality of the CPP and CPPS measures was influenced substantially by the addition of ambient noise. It was anticipated that the CPP measures might serve as a promising digital biomarker in assessing the dysphonia from the early stages of PD.