Voice in Parkinson's Disease: A Machine Learning Study

Investigation of the voice handicaps in Parkinson's disease and determination of the clinical correlates

Speech impairment is a common and disabling symptom of Parkinson's disease (PD). We aimed to reveal the motor, nonmotor, and other clinical factors that might be associated with voice disturbances in PD. Remarkably, we aimed to present a possible specific clinical phenotype more prone to display speech disturbances. We included all the patients with PD who visited our movement disorders clinic between March 2023 and March 2024 and whose information regarding the clinical features and scale results was fully available. In addition to detailed demographic data, comprehensive clinical assessments were performed. We included 232 PD patients with a mean age of 64.4 ± 10.5 y (F/M = 145/87). The median disease duration was 4 y. The comparative analyses of the patients with and without voice handicaps (VH) revealed that patients with VH had higher disease duration and LED. They got higher scores in all the clinical scales, including MDS-UPDRS 1, 2, 3, 4, FOGQ, FES-I, HAM-A, and HDRS revealing a more severe disease stage However, multiple linear regression models revealed only the MDS-UPDRS 4 score, HAM-A score, and MDS-UPDRS-3 (on) score [- 10,658 + 2297*MDS-UPDRS-4 + 0949*HAI + 0549*MDS-UPDRS-3 (on)] as predictors of VHI. Our results support increasing speech problems with higher motor stage, and motor complication score. Besides, we also draw attention to anxiety, which is associated with speech problems in the general community, but only in an experimental study of PD pathology.

Smartphone-derived multidomain features including voice, finger-tapping movement and gait aid early identification of Parkinson's disease

Smart devices can easily capture changes in voice, movements, and gait in people with Parkinson's disease (PD). We investigated whether smartphone-derived multimodal features combined with machine learning algorithms can aid in early PD identification. We recruited 496 participants, split into a training cohort (127 PD patients during "on" phase and 198 age-matched controls) and a test dataset (86 patients during "off" phase and 85 age-matched controls). Multidomain features from smartphone recordings were analyzed using machine learning classifiers with integration of a hyperparameter grid. Single-modality models for voice, hand movements, and gait showed diagnostic values of 0.88, 0.74, and 0.81, respectively, with test dataset values of 0.80, 0.74, and 0.76. An integrated multimodal model using a support vector machine improved performance to 0.86 and achieved 0.82 for identifying early-stage PD during the "off" phase. A smartphone-based integrated multimodality model combining voice, hand movement, and gait shows promise for early PD identification.

Advanced optimization strategies for combining acoustic features and speech recognition error rates in multi-stage classification of Parkinson's disease severity

Recent research has made significant progress with definitively identifying individuals with Parkinson's disease (PD) using speech analysis techniques. However, these studies have often treated the early and advanced stages of PD as equivalent, overlooking the distinct speech impairments and symptoms that can vary significantly across the various stages. This research aims to enhance diagnostic accuracy by utilizing advanced optimization strategies to combine speech recognition results (character error rates) with the acoustic features of vowels for more rigorous diagnostic precision. The dysphonia features of three sustained Korean vowels /아/ (a), /이/ (i), and /우/ (u) were examined for their diversity and strong correlations. Four recognized machine-learning classifiers: Random Forest, Support Vector Machine, k-Nearest Neighbors, and Multi-Layer Perceptron, were employed for consistent and reliable analysis. By fine-tuning the Whisper model specifically for PD speech recognition and optimizing it for each severity level of PD, we significantly improved the discernibility between PD severity levels. This enhancement, when combined with vowel data, allowed for a more precise classification, achieving an improved detection accuracy of 5.87% for a 3-level severity classification over the PD "ON"-state dataset, and an improved detection accuracy of 7.8% for a 3-level severity classification over the PD "OFF"-state dataset. This comprehensive approach not only evaluates the effectiveness of different feature extraction methods but also minimizes the variance across final classification models, thus detecting varying severity levels of PD more effectively.

Normative aging results in degradation of gene networks in a zebra finch basal ganglia nucleus dedicated to vocal behavior

Aging increases brain susceptibility to neurodegenerative diseases, but the mechanisms are not clear. Vocal behavior provides an accessible, reliable, and sensitive biomarker to address this because voice changes in middle age can be early indicators of neurodegenerative diseases. The adult male zebra finch is an excellent model organism for these studies due to well-characterized vocal brain circuitry and strong homology to human brain centers. We performed RNA sequencing of song-dedicated basal ganglia nucleus Area X followed by weighted gene co-expression network analyses to examine changes in gene patterns across younger adult, middle, and older ages. Song-correlated gene networks degrade with age, with modules losing their coherence and migrating to different sets of genes, and changes in connection strength particularly for hub genes including those associated with human speech, Parkinson's, and Alzheimer's diseases. Gene pathway enrichment analyses reveal a lack of ongoing metabolic and biogenic processes in older finches. Our findings provide a robust platform for targeting network hubs in the treatment of neurologically driven human vocal disorders.

Non-invasive detection of Parkinson's disease based on speech analysis and interpretable machine learning

Objective

Parkinson's disease (PD) is a progressive neurodegenerative disorder that significantly impacts motor function and speech patterns. Early detection of PD through non-invasive methods, such as speech analysis, can improve treatment outcomes and quality of life for patients. This study aims to develop an interpretable machine learning model that uses speech recordings and acoustic features to predict PD.

Methods

A dataset of speech recordings from individuals with and without PD was analyzed. The dataset includes features such as fundamental frequency (Fo), jitter, shimmer, noise-to-harmonics ratio (NHR), and non-linear dynamic complexity measures. Exploratory data analysis (EDA) was conducted to identify patterns and relationships in the data. The dataset was split into 70% training and 30% testing sets. To address class imbalance, synthetic minority oversampling technique (SMOTE) was applied. Several machine learning algorithms, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Decision Trees, Random Forests, and Neural Networks, were implemented and evaluated. Model performance was assessed using accuracy, recall, F1 score, and area under the receiver operating characteristic curve (AUC-ROC) metrics. SHapley Additive exPlanations (SHAP) were used to explain the models and evaluate feature contributions.

Results

The analysis revealed that features related to speech instability, such as jitter, shimmer, and NHR, were highly predictive of PD. Non-linear metrics, including Recurrence Plot Dimension Entropy (RPDE) and Pitch Period Entropy (PPE), also made significant contributions to the model's predictive power. Random Forest and Gradient Boosting models achieved the highest performance, with an AUC-ROC of 0.98, recall of 0.95, ensuring minimal false negatives. SHAp values highlighted the importance of fundamental frequency variation and harmonic-to-noise ratio in distinguishing PD patients from healthy individuals.

Conclusion

The developed machine learning model accurately predicts Parkinson's disease using speech recordings, with Random Forest and Gradient Boosting algorithms demonstrating superior performance. Key predictive features include jitter, shimmer, and non-linear dynamic complexity measures. This study provides a reliable, non-invasive tool for early PD detection and underscores the potential of speech analysis in diagnosing neurodegenerative diseases.

Analysis of Voice, Speech, and Language Biomarkers of Parkinson's Disease Collected in a Mixed Reality Setting

This study explores an innovative approach to early Parkinson's disease (PD) detection by analyzing speech data collected using a mixed reality (MR) system. A total of 57 Polish participants, including PD patients and healthy controls, performed five speech tasks while using an MR head-mounted display (HMD). Speech data were recorded and analyzed to extract acoustic and linguistic features, which were then evaluated using machine learning models, including logistic regression, support vector machines (SVMs), random forests, AdaBoost, and XGBoost. The XGBoost model achieved the best performance, with an F1-score of 0.90 ± 0.05 in the story-retelling task. Key features such as MFCCs (mel-frequency cepstral coefficients), spectral characteristics, RASTA-filtered auditory spectrum, and local shimmer were identified as significant in detecting PD-related speech alterations. Additionally, state-of-the-art deep learning models (wav2vec2, HuBERT, and WavLM) were fine-tuned for PD detection. HuBERT achieved the highest performance, with an F1-score of 0.94 ± 0.04 in the diadochokinetic task, demonstrating the potential of deep learning to capture complex speech patterns linked to neurodegenerative diseases. This study highlights the effectiveness of combining MR technology for speech data collection with advanced machine learning (ML) and deep learning (DL) techniques, offering a non-invasive and high-precision approach to PD diagnosis. The findings hold promise for broader clinical applications, advancing the diagnostic landscape for neurodegenerative disorders.

Voice biomarkers as prognostic indicators for Parkinson's disease using machine learning techniques

Many people suffer from Parkinson's disease globally, a complicated neurological condition caused by the deficiency of dopamine, an organic chemical responsible for regulating movement in individuals. Patients with Parkinson face muscle stiffness or rigidity, tremors, vocal impairment, slow movement, loss of facial expressions, and problems with balance and coordination. As there is no cure for Parkinson, early diagnosis can help prevent the progression of this disease. The study explores the potential of vocal measures as significant indicators for early prediction of Parkinson. Different machine learning models such as Support Vector Machine (SVM), Random Forest (RF), Logistic Regression (LR), and Decision Tree (DT) are used to detect Parkinson using voice measures and differentiate between the healthy and Parkinson patients. The dataset contains 195 vocal recordings from 31 patients. The Synthetic Minority Over-Sampling Technique (SMOTE) is used for handling class imbalance to improve the performance of the models. The Principal Component Analysis (PCA) method was used for feature selection. The study uses different parameters to evaluate the model's classification results. The results highlight RF as the most effective model with an accuracy of 94% and a precision of 94%. In addition, SVM achieves an accuracy score of 92%, and precision of 91%. However, with the PCA method, SVM achieves an accuracy of 89%, 92%, and 87% for RF and DT respectively. This study highlights the significance of using vocal features along with advanced machine learning methods to reliably diagnose Parkinson's disease, considering the challenges associated with early detection.

Comparison of Voice Quality in Persian Parkinson Patients With Healthy Counterparts Using Cepstral Peak Prominence and Cepstral Peak Prominence-Smooth and Their Relationship With Disease Severity (UPDRS-III) and Disease Duration

INTRODUCTION

One of the earliest impairments in Parkinson's patients is speech motor dysfunction, which adversely affects the phonation subsystem (voice). To date, acoustic frequency-dependent voice features such as cepstral peak prominence (CPP) and cepstral peak prominence-smooth (CPPS) have not been examined in Persian-speaking Parkinson's patients. This study aims to compare the voice quality of Persian Parkinson's patients with healthy counterparts using CPP and CPPS, as well as to investigate the relationship of these metrics with Unified Parkinson's Disease Rating Scale-Part III (UPDRS-III) and disease duration.

METHOD

This study included 35 Persian Parkinson's patients and 35 healthy individuals. Disease severity was assessed using UPDRS-III. Speech samples (sustained vowel phonation of /ɑ/ and reading of the "Grandfather Passage") were recorded by a microphone. CPP and CPPS were extracted by Praat software.

RESULTS

The results showed that the mean CPP and CPPS in both tasks were significantly lower in the patient group compared with the healthy group (P value ≤ 0.001). Spearman correlation analysis of CPP and CPPS values in both tasks with disease severity revealed a significant negative correlation between CPP and CPPS and UPDRS-III in both tasks (P value ≤ 0.001). However, no significant correlation was observed between these indices and disease duration in any task (P value ≥ 0.001).

CONCLUSION

These cepstral indices effectively distinguish vocal differences between Persian Parkinson's patients and healthy individuals. Additionally, these indices show a significant association with disease severity, underscoring their potential utility in the early diagnosis and monitoring of Parkinson's disease progression through vocal screening, especially when combined with other medical and neurological evaluations. However, this study found no relationship between disease duration and these indices. The absence of such a correlation may be attributed to the medication regimens of the patients.

Molecular Biomarkers in Neurological Diseases: Advances in Diagnosis and Prognosis

Neurological diseases contribute significantly to disability and mortality, necessitating improved diagnostic and prognostic tools. Advances in molecular biomarkers at genomic, transcriptomic, epigenomic, and proteomic levels have facilitated early disease detection. Notably, neurofilament light chain (NfL) serves as a key biomarker of neurodegeneration, while liquid biopsy techniques enable non-invasive monitoring through exosomal tau, α-synuclein, and inflammatory markers. Artificial intelligence (AI) and multi-omics integration further enhance biomarker discovery, promoting precision medicine. A comprehensive literature review was conducted using PubMed, Scopus, and Web of Science to identify studies (2010-2024) on molecular biomarkers in neurodegenerative and neuroinflammatory disorders. Key findings on genomic mutations, transcriptomic signatures, epigenetic modifications, and protein-based biomarkers were analyzed. The findings highlight the potential of liquid biopsy and multi-omics approaches in improving diagnostic accuracy and therapeutic stratification. Genomic, transcriptomic, and proteomic markers demonstrate utility in early detection and disease monitoring. AI-driven analysis enhances biomarker discovery and clinical application. Despite advancements, challenges remain in biomarker validation, standardization, and clinical implementation. Large-scale longitudinal studies are essential to ensure reliability. AI-powered multi-omics analysis may accelerate biomarker application, ultimately improving patient outcomes in neurological diseases.

Intra-individual Variations in Voice Variables Among Individuals With and Without Parkinson's Disease

Introduction Voice changes affect 70 to 90% of individuals with Parkinson's disease (PD). Voice and speech changes in individuals with PD include increased shimmer, increased jitter, reduced harmonics-to-noise ratio (HNR), and changes in fundamental frequency. Studies have identified inter-individual variations in voice variables as PD progresses. However, intra-individual variations in voice variables have not been studied extensively. When individuals without PD experience stress or nervousness, their jitter and shimmer may also increase. Therefore, the purpose of our study was to compare the mean intra-individual variations in voice variables for individuals with PD and those without PD to determine whether the mean intra-individual variations differ between the two groups. Methodology We utilized the "Oxford Parkinson's Disease Detection Dataset," which consists of various biomedical voice measurements, and each individual's voice was measured six or seven times. The changes between each voice measurement for each individual were calculated. Independent samples t-tests were performed to determine significant differences in intra-individual variations in voice variables between individuals with PD and those without PD for all voice variables. Results The independent samples t-tests revealed no statistically significant differences in intra-individual variations between individuals with (n = 24) and without PD (n = 8) for any of the voice variables. For vocal fundamental frequency variables, the mean differences ranged from -1.98e5 (Flo) to 2.58e5 (Fhi). For jitter variables, the mean differences ranged from 1.05e-6 (Jitter(Abs)) to 5.32e-4 (DDP). For shimmer variables, the mean differences ranged from 2.11e-4 (APQ5) to 7.07e2 (Shimmer(dB)). For other variables, the mean differences ranged from -2.76e6 (HNR) to 6.02e4 (spread1). Conclusion Our findings indicate that intra-individual variations in voice variables do not significantly differ between individuals with and without PD. This suggests that intra-individual voice variability may not serve as a distinguishing factor for PD diagnosis. Future research should explore alternative methods to assess intra-individual voice variability and its potential role in PD diagnostics.

Voice EHR: introducing multimodal audio data for health

Introduction

Artificial intelligence (AI) models trained on audio data may have the potential to rapidly perform clinical tasks, enhancing medical decision-making and potentially improving outcomes through early detection. Existing technologies depend on limited datasets collected with expensive recording equipment in high-income countries, which challenges deployment in resource-constrained, high-volume settings where audio data may have a profound impact on health equity.

Methods

This report introduces a novel protocol for audio data collection and a corresponding application that captures health information through guided questions.

Results

To demonstrate the potential of Voice EHR as a biomarker of health, initial experiments on data quality and multiple case studies are presented in this report. Large language models (LLMs) were used to compare transcribed Voice EHR data with data (from the same patients) collected through conventional techniques like multiple choice questions. Information contained in the Voice EHR samples was consistently rated as equally or more relevant to a health evaluation.

Discussion

The HEAR application facilitates the collection of an audio electronic health record ("Voice EHR") that may contain complex biomarkers of health from conventional voice/respiratory features, speech patterns, and spoken language with semantic meaning and longitudinal context-potentially compensating for the typical limitations of unimodal clinical datasets.

Clinical Decision Support Using Speech Signal Analysis: Systematic Scoping Review of Neurological Disorders

BACKGROUND

Digital biomarkers are increasingly used in clinical decision support for various health conditions. Speech features as digital biomarkers can offer insights into underlying physiological processes due to the complexity of speech production. This process involves respiration, phonation, articulation, and resonance, all of which rely on specific motor systems for the preparation and execution of speech. Deficits in any of these systems can cause changes in speech signal patterns. Increasing efforts are being made to develop speech-based clinical decision support systems.

OBJECTIVE

This systematic scoping review investigated the technological revolution and recent digital clinical speech signal analysis trends to understand the key concepts and research processes from clinical and technical perspectives.

METHODS

A systematic scoping review was undertaken in 6 databases guided by a set of research questions. Articles that focused on speech signal analysis for clinical decision-making were identified, and the included studies were analyzed quantitatively. A narrower scope of studies investigating neurological diseases were analyzed using qualitative content analysis.

RESULTS

A total of 389 articles met the initial eligibility criteria, of which 72 (18.5%) that focused on neurological diseases were included in the qualitative analysis. In the included studies, Parkinson disease, Alzheimer disease, and cognitive disorders were the most frequently investigated conditions. The literature explored the potential of speech feature analysis in diagnosis, differentiating between, assessing the severity and monitoring the treatment of neurological conditions. The common speech tasks used were sustained phonations, diadochokinetic tasks, reading tasks, activity-based tasks, picture descriptions, and prompted speech tasks. From these tasks, conventional speech features (such as fundamental frequency, jitter, and shimmer), advanced digital signal processing-based speech features (such as wavelet transformation-based features), and spectrograms in the form of audio images were analyzed. Traditional machine learning and deep learning approaches were used to build predictive models, whereas statistical analysis assessed variable relationships and reliability of speech features. Model evaluations primarily focused on analytical validations. A significant research gap was identified: the need for a structured research process to guide studies toward potential technological intervention in clinical settings. To address this, a research framework was proposed that adapts a design science research methodology to guide research studies systematically.

CONCLUSIONS

The findings highlight how data science techniques can enhance speech signal analysis to support clinical decision-making. By combining knowledge from clinical practice, speech science, and data science within a structured research framework, future research may achieve greater clinical relevance.

Vocal Biomarkers for Parkinson's Disease Classification Using Audio Spectrogram Transformers

Parkinson's disease (PD) is a neurodegenerative disorder affecting motor and non-motor functions, including speech. This study evaluates the effectiveness of the audio spectrogram transformer (AST) model in detecting PD through vocal biomarkers, hypothesizing that its self-attention mechanism would better capture PD related speech impairments compared to traditional deep learning approaches. Speech recordings from 150 participants (100 from PC-GITA: 50 PD, 50 healthy controls (HC); 50 from Italian Parkinson's voice and speech (ITA): 28 PD, 22 HC) were analyzed using the AST model and compared against established architectures including VGG16, VGG19, ResNet18, ResNet34, vision transformer, and swin transformer. Audio preprocessing included sampling rate standardization to 16 kHz and amplitude normalization. The AST model achieved superior classification performance across all datasets: 97.14% accuracy on ITA, 91.67% on Parkinson's Colombian - Grupo de Investigación en Telecomunicaciones Aplicadas (PC-GITA), and 92.73% on the combined dataset. Performance remained consistent across different speech tasks, with particularly strong results in sustained vowel analysis (precision: 0.97 ± 0.03, recall: 0.96 ± 0.03). The model demonstrated robust cross-lingual generalization, outperforming traditional architectures by 5%-10% in accuracy. These results suggest that the AST model provides a reliable, non-invasive method for PD detection through voice analysis, with strong performance across different languages and speech tasks. The model's success in cross-lingual generalization indicates potential for broader clinical application, though validation across more diverse populations is needed for clinical implementation.

Acoustic and Clinical Data Analysis of Vocal Recordings: Pandemic Insights and Lessons

Background/Objectives: The interest in processing human speech and other human-generated audio signals as a diagnostic tool has increased due to the COVID-19 pandemic. The project OSCAR (vOice Screening of CoronA viRus) aimed to develop an algorithm to screen for COVID-19 using a dataset of Portuguese participants with voice recordings and clinical data. Methods: This cross-sectional study aimed to characterise the pattern of sounds produced by the vocal apparatus in patients with SARS-CoV-2 infection documented by a positive RT-PCR test, and to develop and validate a screening algorithm. In Phase II, the algorithm developed in Phase I was tested in a real-world setting. Results: In Phase I, after filtering, the training group consisted of 166 subjects who were effectively available to train the classification model (34.3% SARS-CoV-2 positive/65.7% SARS-CoV-2 negative). Phase II enrolled 58 participants (69.0% SARS-CoV-2 positive/31.0% SARS-CoV-2 negative). The final model achieved a sensitivity of 85%, a specificity of 88.9%, and an F1-score of 84.7%, suggesting voice screening algorithms as an attractive strategy for COVID-19 diagnosis. Conclusions: Our findings highlight the potential of a voice-based detection strategy as an alternative method for respiratory tract screening.

Artificial Intelligence in Laryngology, Broncho-Esophagology, and Sleep Surgery

Technological advancements in laryngology, broncho-esophagology, and sleep surgery have enabled the collection of increasing amounts of complex data for diagnosis and treatment of voice, swallowing, and sleep disorders. Clinicians face challenges in efficiently synthesizing these data for personalized patient care. Artificial intelligence (AI), specifically machine learning and deep learning, offers innovative solutions for processing and interpreting these data, revolutionizing diagnosis and management in these fields, and making care more efficient and effective. In this study, we review recent AI-based innovations in the fields of laryngology, broncho-esophagology, and sleep surgery.

Machine learning and wearable sensors for automated Parkinson's disease diagnosis aid: a systematic review

BACKGROUND

The diagnosis of Parkinson's disease is currently based on clinical evaluation. Despite clinical hallmarks, unfortunately, the error rate is still significant. Low in-vivo diagnostic accuracy of clinical evaluation mainly relies on the lack of quantitative biomarkers for an objective motor performance assessment. Non-invasive technologies, such as wearable sensors, coupled with machine learning algorithms, assess quantitatively and objectively the motor performances, with possible benefits either for in-clinic and at-home settings. We conducted a systematic review of the literature on machine learning algorithms embedded in smart devices in Parkinson's disease diagnosis.

METHODS

Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, we searched PubMed for articles published between December, 2007 and July, 2023, using a search string combining "Parkinson's disease" AND ("healthy" or "control") AND "diagnosis", within the Groups and Outcome domains. Additional search terms included "Algorithm", "Technology" and "Performance".

RESULTS

From 89 identified studies, 47 met the inclusion criteria based on the search string and four additional studies were included based on the Authors' expertise. Gait emerged as the most common parameter analysed by machine learning models, with Support Vector Machines as the prevalent algorithm. The results suggest promising accuracy with complex algorithms like Random Forest, Support Vector Machines, and K-Nearest Neighbours.

DISCUSSION

Despite the promise shown by machine learning algorithms, real-world applications may still face limitations. This review suggests that integrating machine learning with wearable sensors has the potential to improve Parkinson's disease diagnosis. These tools could provide clinicians with objective data, potentially aiding in earlier detection.

Oral-diadochokinesis between Parkinson's disease and neurotypical elderly among Malaysian-Malay speakers

BACKGROUND

Parkinson's disease (PD) has an impact on speech production, manifesting in various ways including alterations in voice quality, challenges in articulating sounds and a decrease in speech rate. Numerous investigations have been conducted to ascertain the oral-diadochokinesis (O-DDK) rate in individuals with PD. However, the existing literature lacks exploration of such O-DDK rates in Malaysia and does not provide consistent evidence regarding the advantage of real-word repetition.

AIMS

To explore the effect of gender, stimuli type and PD status and their interactions on the O-DDK rates among Malaysian-Malay speakers.

METHODS & PROCEDURES

O-DDK performance of 62 participants (29 individuals with PD and 33 healthy elderly) using a non-word ('pataka'), a Malay real-word ('patahkan') and an English real-word ('buttercake') was audio recorded. The number of syllables produced in 8 s was counted. A hierarchical linear modelling was performed to investigate the effects of stimuli type (non-word, Malay real-word, English real-word), PD status (yes, no), gender (male, female) and their interactions on the O-DDK rate. The model accounted for participants' age as well as the nesting of repeated measurements within participants, thereby providing unbiased estimates of the effects.

OUTCOMES & RESULTS

The stimuli effect was significant (p < 0.0001). Malay real-word showed the lowest O-DDK rate (5.03 ± 0.11 syllables/s), followed by English real-word (5.25 ± 0.11 syllables/s) and non-word (5.42 ± 0.11 syllables/s). Individuals with PD showed a significantly lower O-DDK rate compared to healthy elderly (4.73 ± 0.15 syllables/s vs. 5.74 ± 0.14 syllables/s, adjusted p < 0.001). A subsequent analysis indicated that the O-DDK rate declined in a quadratic pattern. However, neither gender nor age effects were observed. Additionally, no significant two-way interactions were found between stimuli type, PD status and gender (all p > 0.05). Therefore, the choice of stimuli type has no or only limited effect considering the use of O-DDK tests in clinical practice for diagnostic purposes.

CONCLUSIONS & IMPLICATIONS

The observed slowness in O-DDK among individuals with PD can be attributed to the impact of the movement disorder, specifically bradykinesia, on the physiological aspects of speech production. Speech-language pathologists can gain insights into the impact of PD on speech production and tailor appropriate intervention strategies to address the specific needs of individuals with PD according to disease stages.

WHAT THIS PAPER ADDS

What is already known on this subject The observed slowness in O-DDK rates among individuals with PD may stem from the movement disorder's effects on the physiological aspects of speech production, particularly bradykinesia. However, there is a lack of consistent evidence regarding the influence of real-word repetition and how O-DDK rates vary across different PD stages. What this study adds to existing knowledge The O-DDK rates decline in a quadratic pattern as the PD progresses. The research provides insights into the advantage of real-word repetition in assessing O-DDK rates, with Malay real-word showing the lowest O-DDK rate, followed by English real-word and non-word. What are the potential or actual clinical implications of this work? Speech-language pathologists can better understand the evolving nature of speech motor impairments as PD progresses. This insight enables them to design targeted intervention strategies that are sensitive to the specific needs and challenges associated with each PD stage. This finding can guide clinicians in selecting appropriate assessment tools for evaluating speech motor function in PD patients.

Association analyses of apolipoprotein E genotypes and cognitive performance in patients with Parkinson's disease

BACKGROUND

Cognitive impairment is a common non-motor symptom of Parkinson's disease (PD). The apolipoprotein E (APOE) ε4 genotype increases the risk of Alzheimer's disease (AD). However, the effect of APOEε4 on cognitive function of PD patients remains unclear. In this study, we aimed to understand whether and how carrying APOEε4 affects cognitive performance in patients with early-stage and advanced PD.

METHODS

A total of 119 Chinese early-stage PD patients were recruited. Movement Disorder Society Unified Parkinson's Disease Rating Scale, Hamilton anxiety scale, Hamilton depression scale, non-motor symptoms scale, Mini-mental State Examination, Montreal Cognitive Assessment, and Fazekas scale were evaluated. APOE genotypes were determined by polymerase chain reactions and direct sequencing. Demographic and clinical information of 521 early-stage and 262 advanced PD patients were obtained from Parkinson's Progression Marker Initiative (PPMI).

RESULTS

No significant difference in cognitive performance was found between ApoEε4 carriers and non-carriers in early-stage PD patients from our cohort and PPMI. The cerebrospinal fluid (CSF) Amyloid Beta 42 (Aβ42) level was significantly lower in ApoEε4 carrier than non-carriers in early-stage PD patients from PPMI. In advanced PD patients from PPMI, the BJLOT, HVLT retention and SDMT scores seem to be lower in ApoEε4 carriers without reach the statistical significance.

CONCLUSIONS

APOEε4 carriage does not affect the cognitive performance of early-stage PD patients. However, it may promote the decline of CSF Aβ42 level and the associated amyloidopathy, which is likely to further contribute to the cognitive dysfunction of PD patients in the advanced stage.

Leveraging Deep Learning for Fine-Grained Categorization of Parkinson's Disease Progression Levels through Analysis of Vocal Acoustic Patterns

Speech impairments often emerge as one of the primary indicators of Parkinson's disease (PD), albeit not readily apparent in its early stages. While previous studies focused predominantly on binary PD detection, this research explored the use of deep learning models to automatically classify sustained vowel recordings into healthy controls, mild PD, or severe PD based on motor symptom severity scores. Popular convolutional neural network (CNN) architectures, VGG and ResNet, as well as vision transformers, Swin, were fine-tuned on log mel spectrogram image representations of the segmented voice data. Furthermore, the research investigated the effects of audio segment lengths and specific vowel sounds on the performance of these models. The findings indicated that implementing longer segments yielded better performance. The models showed strong capability in distinguishing PD from healthy subjects, achieving over 95% precision. However, reliably discriminating between mild and severe PD cases remained challenging. The VGG16 achieved the best overall classification performance with 91.8% accuracy and the largest area under the ROC curve. Furthermore, focusing analysis on the vowel /u/ could further improve accuracy to 96%. Applying visualization techniques like Grad-CAM also highlighted how CNN models focused on localized spectrogram regions while transformers attended to more widespread patterns. Overall, this work showed the potential of deep learning for non-invasive screening and monitoring of PD progression from voice recordings, but larger multi-class labeled datasets are needed to further improve severity classification.

Artificial intelligence of imaging and clinical neurological data for predictive, preventive and personalized (P3) medicine for Parkinson Disease: The NeuroArtP3 protocol for a multi-center research study

BACKGROUND

The burden of Parkinson Disease (PD) represents a key public health issue and it is essential to develop innovative and cost-effective approaches to promote sustainable diagnostic and therapeutic interventions. In this perspective the adoption of a P3 (predictive, preventive and personalized) medicine approach seems to be pivotal. The NeuroArtP3 (NET-2018-12366666) is a four-year multi-site project co-funded by the Italian Ministry of Health, bringing together clinical and computational centers operating in the field of neurology, including PD.

OBJECTIVE

The core objectives of the project are: i) to harmonize the collection of data across the participating centers, ii) to structure standardized disease-specific datasets and iii) to advance knowledge on disease's trajectories through machine learning analysis.

METHODS

The 4-years study combines two consecutive research components: i) a multi-center retrospective observational phase; ii) a multi-center prospective observational phase. The retrospective phase aims at collecting data of the patients admitted at the participating clinical centers. Whereas the prospective phase aims at collecting the same variables of the retrospective study in newly diagnosed patients who will be enrolled at the same centers.

RESULTS

The participating clinical centers are the Provincial Health Services (APSS) of Trento (Italy) as the center responsible for the PD study and the IRCCS San Martino Hospital of Genoa (Italy) as the promoter center of the NeuroartP3 project. The computational centers responsible for data analysis are the Bruno Kessler Foundation of Trento (Italy) with TrentinoSalute4.0 -Competence Center for Digital Health of the Province of Trento (Italy) and the LISCOMPlab University of Genoa (Italy).

CONCLUSIONS

The work behind this observational study protocol shows how it is possible and viable to systematize data collection procedures in order to feed research and to advance the implementation of a P3 approach into the clinical practice through the use of AI models.

Stakeholder perspectives on ethical and trustworthy voice AI in health care

Objective

Voice as a health biomarker using artificial intelligence (AI) is gaining momentum in research. The noninvasiveness of voice data collection through accessible technology (such as smartphones, telehealth, and ambient recordings) or within clinical contexts means voice AI may help address health disparities and promote the inclusion of marginalized communities. However, the development of AI-ready voice datasets free from bias and discrimination is a complex task. The objective of this study is to better understand the perspectives of engaged and interested stakeholders regarding ethical and trustworthy voice AI, to inform both further ethical inquiry and technology innovation.

Methods

A questionnaire was administered to voice AI experts, clinicians, scholars, patients, trainees, and policy-makers who participated at the 2023 Voice AI Symposium organized by the Bridge2AI-Voice AI Consortium. The survey used a mix of Likert scale, ranking and open-ended questions. A total of 27 stakeholders participated in the study.

Results

The main results of the study are the identification of priorities in terms of ethical issues, an initial definition of ethically sourced data for voice AI, insights into the use of synthetic voice data, and proposals for acting on the trustworthiness of voice AI. The study shows a diversity of perspectives and adds nuance to the planning and development of ethical and trustworthy voice AI.

Conclusions

This study represents the first stakeholder survey related to voice as a biomarker of health published to date. This study sheds light on the critical importance of ethics and trustworthiness in the development of voice AI technologies for health applications.

Multitask and Transfer Learning Approach for Joint Classification and Severity Estimation of Dysphonia

OBJECTIVE

Despite speech being the primary communication medium, it carries valuable information about a speaker's health, emotions, and identity. Various conditions can affect the vocal organs, leading to speech difficulties. Extensive research has been conducted by voice clinicians and academia in speech analysis. Previous approaches primarily focused on one particular task, such as differentiating between normal and dysphonic speech, classifying different voice disorders, or estimating the severity of voice disorders.

METHODS AND PROCEDURES

This study proposes an approach that combines transfer learning and multitask learning (MTL) to simultaneously perform dysphonia classification and severity estimation. Both tasks use a shared representation; network is learned from these shared features. We employed five computer vision models and changed their architecture to support multitask learning. Additionally, we conducted binary 'healthy vs. dysphonia' and multiclass 'healthy vs. organic and functional dysphonia' classification using multitask learning, with the speaker's sex as an auxiliary task.

RESULTS

The proposed method achieved improved performance across all classification metrics compared to single-task learning (STL), which only performs classification or severity estimation. Specifically, the model achieved F1 scores of 93% and 90% in MTL and STL, respectively. Moreover, we observed considerable improvements in both classification tasks by evaluating beta values associated with the weight assigned to the sex-predicting auxiliary task. MTL achieved an accuracy of 77% compared to the STL score of 73.2%. However, the performance of severity estimation in MTL was comparable to STL.

CONCLUSION

Our goal is to improve how voice pathologists and clinicians understand patients' conditions, make it easier to track their progress, and enhance the monitoring of vocal quality and treatment procedures. Clinical and Translational Impact Statement: By integrating both classification and severity estimation of dysphonia using multitask learning, we aim to enable clinicians to gain a better understanding of the patient's situation, effectively monitor their progress and voice quality.

Artificial Intelligence Procedure for the Screening of Genetic Syndromes Based on Voice Characteristics

Perceptual and statistical evidence has highlighted voice characteristics of individuals affected by genetic syndromes that differ from those of normophonic subjects. In this paper, we propose a procedure for systematically collecting such pathological voices and developing AI-based automated tools to support differential diagnosis. Guidelines on the most appropriate recording devices, vocal tasks, and acoustical parameters are provided to simplify, speed up, and make the whole procedure homogeneous and reproducible. The proposed procedure was applied to a group of 56 subjects affected by Costello syndrome (CS), Down syndrome (DS), Noonan syndrome (NS), and Smith-Magenis syndrome (SMS). The entire database was divided into three groups: pediatric subjects (PS; individuals < 12 years of age), female adults (FA), and male adults (MA). In line with the literature results, the Kruskal-Wallis test and post hoc analysis with Dunn-Bonferroni test revealed several significant differences in the acoustical features not only between healthy subjects and patients but also between syndromes within the PS, FA, and MA groups. Machine learning provided a k-nearest-neighbor classifier with 86% accuracy for the PS group, a support vector machine (SVM) model with 77% accuracy for the FA group, and an SVM model with 84% accuracy for the MA group. These preliminary results suggest that the proposed method based on acoustical analysis and AI could be useful for an effective, non-invasive automatic characterization of genetic syndromes. In addition, clinicians could benefit in the case of genetic syndromes that are extremely rare or present multiple variants and facial phenotypes.

A multimodal screening system for elderly neurological diseases based on deep learning

In this paper, we propose a deep-learning-based algorithm for screening neurological diseases. We proposed various examination protocols for screening neurological diseases and collected data by video-recording persons performing these protocols. We converted video data into human landmarks that capture action information with a much smaller data dimension. We also used voice data which are also effective indicators of neurological disorders. We designed a subnetwork for each protocol to extract features from landmarks or voice and a feature aggregator that combines all the information extracted from the protocols to make a final decision. Multitask learning was applied to screen two neurological diseases. To capture meaningful information about these human landmarks and voices, we applied various pre-trained models to extract preliminary features. The spatiotemporal characteristics of landmarks are extracted using a pre-trained graph neural network, and voice features are extracted using a pre-trained time-delay neural network. These extracted high-level features are then passed onto the subnetworks and an additional feature aggregator that are simultaneously trained. We also used various data augmentation techniques to overcome the shortage of data. Using a frame-length staticizer that considers the characteristics of the data, we can capture momentary tremors without wasting information. Finally, we examine the effectiveness of different protocols and different modalities (different body parts and voice) through extensive experiments. The proposed method achieves AUC scores of 0.802 for stroke and 0.780 for Parkinson's disease, which is effective for a screening system.

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.

Effects of deep brain stimulation of the subthalamic nucleus on patients with Parkinson's disease: a machine-learning voice analysis

Introduction

Deep brain stimulation of the subthalamic nucleus (STN-DBS) can exert relevant effects on the voice of patients with Parkinson's disease (PD). In this study, we used artificial intelligence to objectively analyze the voices of PD patients with STN-DBS.

Materials and methods

In a cross-sectional study, we enrolled 108 controls and 101 patients with PD. The cohort of PD was divided into two groups: the first group included 50 patients with STN-DBS, and the second group included 51 patients receiving the best medical treatment. The voices were clinically evaluated using the Unified Parkinson's Disease Rating Scale part-III subitem for voice (UPDRS-III-v). We recorded and then analyzed voices using specific machine-learning algorithms. The likelihood ratio (LR) was also calculated as an objective measure for clinical-instrumental correlations.

Results

Clinically, voice impairment was greater in STN-DBS patients than in those who received oral treatment. Using machine learning, we objectively and accurately distinguished between the voices of STN-DBS patients and those under oral treatments. We also found significant clinical-instrumental correlations since the greater the LRs, the higher the UPDRS-III-v scores.

Discussion

STN-DBS deteriorates speech in patients with PD, as objectively demonstrated by machine-learning voice analysis.

Toward Personalized Medicine Approaches for Parkinson Disease Using Digital Technologies

Parkinson disease (PD) is a complex neurodegenerative disorder that afflicts over 10 million people worldwide, resulting in debilitating motor and cognitive impairment. In the United States alone (with approximately 1 million cases), the economic burden for treating and caring for persons with PD exceeds US $50 billion and myriad therapeutic approaches are under development, including both symptomatic- and disease-modifying agents. The challenges presented in addressing PD are compounded by observations that numerous, statistically distinct patient phenotypes present with a wide variety of motor and nonmotor symptomatic profiles, varying responses to current standard-of-care symptom-alleviating medications (L-DOPA and dopaminergic agonists), and different disease trajectories. The existence of these differing phenotypes highlights the opportunities in personalized approaches to symptom management and disease control. The prodromal period of PD can span across several decades, allowing the potential to leverage the unique array of composite symptoms presented to trigger early interventions. This may be especially beneficial as disease progression in PD (alongside Alzheimer disease and Huntington disease) may be influenced by biological processes such as oxidative stress, offering the potential for individual lifestyle factors to be tailored to delay disease onset. In this viewpoint, we offer potential scenarios where emerging diagnostic and monitoring strategies might be tailored to the individual patient under the tenets of P4 medicine (predict, prevent, personalize, and participate). These approaches may be especially relevant as the causative factors and biochemical pathways responsible for the observed neurodegeneration in patients with PD remain areas of fluid debate. The numerous observational patient cohorts established globally offer an excellent opportunity to test and refine approaches to detect, characterize, control, modify the course, and ultimately stop progression of this debilitating disease. Such approaches may also help development of parallel interventive strategies in other diseases such as Alzheimer disease and Huntington disease, which share common traits and etiologies with PD. In this overview, we highlight near-term opportunities to apply P4 medicine principles for patients with PD and introduce the concept of composite orthogonal patient monitoring.

Hybrid Machine Learning Framework for Multistage Parkinson's Disease Classification Using Acoustic Features of Sustained Korean Vowels

Recent research has achieved a great classification rate for separating healthy people from those with Parkinson's disease (PD) using speech and the voice. However, these studies have primarily treated early and advanced stages of PD as equal entities, neglecting the distinctive speech impairments and other symptoms that vary across the different stages of the disease. To address this limitation, and improve diagnostic precision, this study assesses the selected acoustic features of dysphonia, as they relate to PD and the Hoehn and Yahr stages, by combining various preprocessing techniques and multiple classification algorithms, to create a comprehensive and robust solution for classification tasks. The dysphonia features extracted from the three sustained Korean vowels /아/(a), /이/(i), and /우/(u) exhibit diversity and strong correlations. To address this issue, the analysis of variance F-Value feature selection classifier from scikit-learn was employed, to identify the topmost relevant features. Additionally, to overcome the class imbalance problem, the synthetic minority over-sampling technique was utilized. To ensure fair comparisons, and mitigate the influence of individual classifiers, four commonly used machine learning classifiers, namely random forest (RF), support vector machine (SVM), k-nearest neighbor (kNN), and multi-layer perceptron (MLP), were employed. This approach enables a comprehensive evaluation of the feature extraction methods, and minimizes the variance in the final classification models. The proposed hybrid machine learning pipeline using the acoustic features of sustained vowels efficiently detects the early and mid-advanced stages of PD with a detection accuracy of 95.48%, and with a detection accuracy of 86.62% for the 4-stage, and a detection accuracy of 89.48% for the 3-stage classification of PD. This study successfully demonstrates the significance of utilizing the diverse acoustic features of dysphonia in the classification of PD and its stages.

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.

Vision Transformer for Parkinson's Disease Classification using Multilingual Sustained Vowel Recordings

Parkinson's disease (PD) is the 2nd most prevalent neurodegenerative disease in the world. Thus, the early detection of PD has recently been the subject of several scientific and commercial studies. In this paper, we propose a pipeline using Vision Transformer applied to mel-spectrograms for PD classification using multilingual sustained vowel recordings. Furthermore, our proposed transformed-based model shows a great potential to use voice as a single modality biomarker for automatic PD detection without language restrictions, a wide range of vowels, with an F1-score equal to 0.78. The results of our study fall within the range of the estimated prevalence of voice and speech disorders in Parkinson's disease, which ranges from 70-90%. Our study demonstrates a high potential for adaptation in clinical decision-making, allowing for increasingly systematic and fast diagnosis of PD with the potential for use in telemedicine.Clinical relevance- There is an urgent need to develop non invasive biomarker of Parkinson's disease effective enough to detect the onset of the disease to introduce neuroprotective treatment at the earliest stage possible and to follow the results of that intervention. Voice disorders in PD are very frequent and are expected to be utilized as an early diagnostic biomarker. The voice analysis using deep neural networks open new opportunities to assess neurodegenerative diseases' symptoms, for fast diagnosis-making, to guide treatment initiation, and risk prediction. The detection accuracy for voice biomarkers according to our method reached close to the maximum achievable value.

Acoustic analysis in stuttering: a machine-learning study

Background

Stuttering is a childhood-onset neurodevelopmental disorder affecting speech fluency. The diagnosis and clinical management of stuttering is currently based on perceptual examination and clinical scales. Standardized techniques for acoustic analysis have prompted promising results for the objective assessment of dysfluency in people with stuttering (PWS).

Objective

We assessed objectively and automatically voice in stuttering, through artificial intelligence (i.e., the support vector machine - SVM classifier). We also investigated the age-related changes affecting voice in stutterers, and verified the relevance of specific speech tasks for the objective and automatic assessment of stuttering.

Methods

Fifty-three PWS (20 children, 33 younger adults) and 71 age-/gender-matched controls (31 children, 40 younger adults) were recruited. Clinical data were assessed through clinical scales. The voluntary and sustained emission of a vowel and two sentences were recorded through smartphones. Audio samples were analyzed using a dedicated machine-learning algorithm, the SVM to compare PWS and controls, both children and younger adults. The receiver operating characteristic (ROC) curves were calculated for a description of the accuracy, for all comparisons. The likelihood ratio (LR), was calculated for each PWS during all speech tasks, for clinical-instrumental correlations, by using an artificial neural network (ANN).

Results

Acoustic analysis based on machine-learning algorithm objectively and automatically discriminated between the overall cohort of PWS and controls with high accuracy (88%). Also, physiologic ageing crucially influenced stuttering as demonstrated by the high accuracy (92%) of machine-learning analysis when classifying children and younger adults PWS. The diagnostic accuracies achieved by machine-learning analysis were comparable for each speech task. The significant clinical-instrumental correlations between LRs and clinical scales supported the biological plausibility of our findings.

Conclusion

Acoustic analysis based on artificial intelligence (SVM) represents a reliable tool for the objective and automatic recognition of stuttering and its relationship with physiologic ageing. The accuracy of the automatic classification is high and independent of the speech task. Machine-learning analysis would help clinicians in the objective diagnosis and clinical management of stuttering. The digital collection of audio samples here achieved through smartphones would promote the future application of the technique in a telemedicine context (home environment).

Robust and language-independent acoustic features in Parkinson's disease

Introduction

The analysis of vocal samples from patients with Parkinson's disease (PDP) can be relevant in supporting early diagnosis and disease monitoring. Intriguingly, speech analysis embeds several complexities influenced by speaker characteristics (e.g., gender and language) and recording conditions (e.g., professional microphones or smartphones, supervised, or non-supervised data collection). Moreover, the set of vocal tasks performed, such as sustained phonation, reading text, or monologue, strongly affects the speech dimension investigated, the feature extracted, and, as a consequence, the performance of the overall algorithm.

Methods

We employed six datasets, including a cohort of 176 Healthy Control (HC) participants and 178 PDP from different nationalities (i.e., Italian, Spanish, Czech), recorded in variable scenarios through various devices (i.e., professional microphones and smartphones), and performing several speech exercises (i.e., vowel phonation, sentence repetition). Aiming to identify the effectiveness of different vocal tasks and the trustworthiness of features independent of external co-factors such as language, gender, and data collection modality, we performed several intra- and inter-corpora statistical analyses. In addition, we compared the performance of different feature selection and classification models to evaluate the most robust and performing pipeline.

Results

According to our results, the combined use of sustained phonation and sentence repetition should be preferred over a single exercise. As for the set of features, the Mel Frequency Cepstral Coefficients demonstrated to be among the most effective parameters in discriminating between HC and PDP, also in the presence of heterogeneous languages and acquisition techniques.

Conclusion

Even though preliminary, the results of this work can be exploited to define a speech protocol that can effectively capture vocal alterations while minimizing the effort required to the patient. Moreover, the statistical analysis identified a set of features minimally dependent on gender, language, and recording modalities. This discloses the feasibility of extensive cross-corpora tests to develop robust and reliable tools for disease monitoring and staging and PDP follow-up.

Parkinson's disease therapy: what lies ahead?

The worldwide prevalence of Parkinson's disease (PD) has been constantly increasing in the last decades. With rising life expectancy, a longer disease duration in PD patients is observed, further increasing the need and socioeconomic importance of adequate PD treatment. Today, PD is exclusively treated symptomatically, mainly by dopaminergic stimulation, while efforts to modify disease progression could not yet be translated to the clinics. New formulations of approved drugs and treatment options of motor fluctuations in advanced stages accompanied by telehealth monitoring have improved PD patients care. In addition, continuous improvement in the understanding of PD disease mechanisms resulted in the identification of new pharmacological targets. Applying novel trial designs, targeting of pre-symptomatic disease stages, and the acknowledgment of PD heterogeneity raise hopes to overcome past failures in the development of drugs for disease modification. In this review, we address these recent developments and venture a glimpse into the future of PD therapy in the years to come.

Acoustic Analysis of Speech for Screening for Suicide Risk: Machine Learning Classifiers for Between- and Within-Person Evaluation of Suicidality

BACKGROUND

Assessing a patient's suicide risk is challenging for health professionals because it depends on voluntary disclosure by the patient and often has limited resources. The application of novel machine learning approaches to determine suicide risk has clinical utility.

OBJECTIVE

This study aimed to investigate cross-sectional and longitudinal approaches to assess suicidality based on acoustic voice features of psychiatric patients using artificial intelligence.

METHODS

We collected 348 voice recordings during clinical interviews of 104 patients diagnosed with mood disorders at baseline and 2, 4, 8, and 12 months after recruitment. Suicidality was assessed using the Beck Scale for Suicidal Ideation and suicidal behavior using the Columbia Suicide Severity Rating Scale. The acoustic features of the voice, including temporal, formal, and spectral features, were extracted from the recordings. A between-person classification model that examines the vocal characteristics of individuals cross sectionally to detect individuals at high risk for suicide and a within-person classification model that detects considerable worsening of suicidality based on changes in acoustic features within an individual were developed and compared. Internal validation was performed using 10-fold cross validation of audio data from baseline to 2-month and external validation was performed using data from 2 to 4 months.

RESULTS

A combined set of 12 acoustic features and 3 demographic variables (age, sex, and past suicide attempts) were included in the single-layer artificial neural network for the between-person classification model. Furthermore, 13 acoustic features were included in the extreme gradient boosting machine learning algorithm for the within-person model. The between-person classifier was able to detect high suicidality with 69% accuracy (sensitivity 74%, specificity 62%, area under the receiver operating characteristic curve 0.62), whereas the within-person model was able to predict worsening suicidality over 2 months with 79% accuracy (sensitivity 68%, specificity 84%, area under receiver operating characteristic curve 0.67). The second model showed 62% accuracy in predicting increased suicidality in external sets.

CONCLUSIONS

Within-person analysis using changes in acoustic features within an individual is a promising approach to detect increased suicidality. Automated analysis of voice can be used to support the real-time assessment of suicide risk in primary care or telemedicine.

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson's Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

Parkinson's Disease (PD) is one of the most common non-curable neurodegenerative diseases. Diagnosis is achieved clinically on the basis of different symptoms with considerable delays from the onset of neurodegenerative processes in the central nervous system. In this study, we investigated early and full-blown PD patients based on the analysis of their voice characteristics with the aid of the most commonly employed machine learning (ML) techniques. A custom dataset was made with hi-fi quality recordings of vocal tasks gathered from Italian healthy control subjects and PD patients, divided into early diagnosed, off-medication patients on the one hand, and mid-advanced patients treated with L-Dopa on the other. Following the current state-of-the-art, several ML pipelines were compared usingdifferent feature selection and classification algorithms, and deep learning was also explored with a custom CNN architecture. Results show how feature-based ML and deep learning achieve comparable results in terms of classification, with KNN, SVM and naïve Bayes classifiers performing similarly, with a slight edge for KNN. Much more evident is the predominance of CFS as the best feature selector. The selected features act as relevant vocal biomarkers capable of differentiating healthy subjects, early untreated PD patients and mid-advanced L-Dopa treated patients.

An Analysis of Vocal Features for Parkinson’s Disease Classification Using Evolutionary Algorithms

Parkinson’s Disease (PD) is a brain disorder that causes uncontrollable movements. According to estimation, roughly ten million individuals worldwide have had or are developing PD. This disorder can have severe consequences that affect the patient’s daily life. Therefore, several previous works have worked on PD detection. Automatic Parkinson’s Disease detection in voice recordings can be an innovation compared to other costly methods of ruling out examinations since the nature of this disease is unpredictable and non-curable. Analyzing the collected vocal records will detect essential patterns, and timely recommendations on appropriate treatments will be extremely helpful. This research proposed a machine learning-based approach for classifying healthy people from people with the disease utilizing Grey Wolf Optimization (GWO) for feature selection, along with Light Gradient Boosted Machine (LGBM) to optimize the model performance. The proposed method shows highly competitive results and has the ability to be developed further and implemented in a real-world setting.

Clinical neurophysiology of Parkinson's disease and parkinsonism

•

This review is part of the series on the clinical neurophysiology of movement disorders and focuses on Parkinson’s disease and parkinsonism.

•

The pathophysiology of cardinal parkinsonian motor symptoms and myoclonus are reviewed.

•

The recordings from microelectrode and deep brain stimulation electrodes are reported in detail.

This review is part of the series on the clinical neurophysiology of movement disorders. It focuses on Parkinson’s disease and parkinsonism. The topics covered include the pathophysiology of tremor, rigidity and bradykinesia, balance and gait disturbance and myoclonus in Parkinson’s disease. The use of electroencephalography, electromyography, long latency reflexes, cutaneous silent period, studies of cortical excitability with single and paired transcranial magnetic stimulation, studies of plasticity, intraoperative microelectrode recordings and recording of local field potentials from deep brain stimulation, and electrocorticography are also reviewed. In addition to advancing knowledge of pathophysiology, neurophysiological studies can be useful in refining the diagnosis, localization of surgical targets, and help to develop novel therapies for Parkinson’s disease.