Voice characteristics from isolated rapid eye movement sleep behavior disorder to early Parkinson's disease

Digital Biomarkers for Parkinson Disease: Bibliometric Analysis and a Scoping Review of Deep Learning for Freezing of Gait

BACKGROUND

With the rapid development of digital biomarkers in Parkinson disease (PD) research, it has become increasingly important to explore the current research trends and key areas of focus.

OBJECTIVE

This study aimed to comprehensively evaluate the current status, hot spots, and future trends of global PD biomarker research, and provide a systematic review of deep learning models for freezing of gait (FOG) digital biomarkers.

METHODS

This study used bibliometric analysis based on the Web of Science Core Collection database to conduct a comprehensive analysis of the multidimensional landscape of Parkinson digital biomarkers. After identifying research hot spots, the study also followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines for a scoping review of deep learning models for FOG from 5 databases: Web of Science, PubMed, IEEE Xplore, Embase, and Google Scholar.

RESULTS

A total of 750 studies were included in the bibliometric analysis, and 40 studies were included in the scoping review. The analysis revealed a growing number of related publications, with 3700 researchers contributing. Neurology had the highest average annual participation rate (12.46/19, 66%). The United States contributed the most research (192/1171, 16.4%), with 210 participating institutions, which was the highest among all countries. In the study of deep learning models for FOG, the average accuracy of the models was 0.92, sensitivity was 0.88, specificity was 0.90, and area under the curve was 0.91. In addition, 31 (78%) studies indicated that the best models were primarily convolutional neural networks or convolutional neural networks-based architectures.

CONCLUSIONS

Research on digital biomarkers for PD is currently at a stable stage of development, with widespread global interest from countries, institutions, and researchers. However, challenges remain, including insufficient interdisciplinary and interinstitutional collaboration, as well as a lack of corporate funding for related projects. Current research trends primarily focus on motor-related studies, particularly FOG monitoring. However, deep learning models for FOG still lack external validation and standardized performance reporting. Future research will likely progress toward deeper applications of artificial intelligence, enhanced interinstitutional collaboration, comprehensive analysis of different data types, and the exploration of digital biomarkers for a broader range of Parkinson symptoms.

TRIAL REGISTRATION

Open Science Foundation (OSF Registries) OSF.IO/RG8Y3; https://doi.org/10.17605/OSF.IO/RG8Y3.

Prodromal Parkinson's Disease: A Snapshot of the Landscape

Early observations of specific nonmotor and subtle motor symptoms preceding clinical diagnosis of Parkinson's disease (PD) have paved the way for prodromal PD research, significantly propelling our understanding of early, subclinical stages of neurodegeneration. Prodromal PD has emerged as a complex concept with some researchers suggesting that the period before PD onset is divided into the "at-risk," "preclinical," and "prodromal" phases. Advances in genetic, imaging, laboratory, and digital technologies have enabled the identification of pathophysiological patterns and the potential development of diagnostic, progressive, and therapeutic biomarkers, which could lead to early PD detection and intervention.

A cross-language speech model for detection of Parkinson's disease

Speech change is a biometric marker for Parkinson's disease (PD). However, evaluating speech variability across diverse languages is challenging. We aimed to develop a cross-language algorithm differentiating between PD patients and healthy controls using a Taiwanese and Korean speech data set. We recruited 299 healthy controls and 347 patients with PD from Taiwan and Korea. Participants with PD underwent smartphone-based speech recordings during the "on" phase. Each Korean participant performed various speech texts, while the Taiwanese participant read a standardized, fixed-length article. Korean short-speech (≦15 syllables) and long-speech (> 15 syllables) recordings were combined with the Taiwanese speech dataset. The merged dataset was split into a training set (controls vs. early-stage PD) and a validation set (controls vs. advanced-stage PD) to evaluate the model's effectiveness in differentiating PD patients from controls across languages based on speech length. Numerous acoustic and linguistic speech features were extracted and combined with machine learning algorithms to distinguish PD patients from controls. The area under the receiver operating characteristic (AUROC) curve was calculated to assess diagnostic performance. Random forest and AdaBoost classifiers showed an AUROC 0.82 for distinguishing patients with early-stage PD from controls. In the validation cohort, the random forest algorithm maintained this value (0.90) for discriminating advanced-stage PD patients. The model showed superior performance in the combined language cohort (AUROC 0.90) than either the Korean (AUROC 0.87) or Taiwanese (AUROC 0.88) cohorts individually. However, with another merged speech data set of short-speech recordings < 25 characters, the diagnostic performance to identify early-stage PD patients from controls dropped to 0.72 and showed a further limited ability to discriminate advanced-stage patients. Leveraging multifaceted speech features, including both acoustic and linguistic characteristics, could aid in distinguishing PD patients from healthy individuals, even across different languages.

Multimodal diagnostic tools and advanced data models for detection of prodromal Parkinson's disease: a scoping review

BACKGROUND

Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by the loss of dopaminergic neurons in the substantia nigra pars compacta. PD is diagnosed by a combination of motor symptoms including bradykinesia, resting tremors, rigidity and postural instability. Prodromal PD is the stage preceding the onset of classic motor symptoms of PD. The diagnosis of prodromal PD remains challenging despite many available diagnostic modalities.

AIM

This scoping review aims to investigate and explore the current diagnostic modalities used to detect prodromal PD, focusing particularly on multimodal imaging analysis and AI-based approaches.

METHODS

We adhered to the PRISMA-SR guidelines for scoping reviews. We conducted a comprehensive literature search at multiple databases such as PubMed, Scopus, Web of Science, and the Cochrane Library from inception to July 2024, using keywords related to prodromal PD and diagnostic modalities. We included studies based on predefined inclusion and exclusion criteria and performed data extraction using a standardized form.

RESULTS

The search included 9 studies involving 567 patients with prodromal PD and 35,643 control. Studies utilized various diagnostic approaches including neuroimaging techniques and AI-driven models. sensitivity ranging from 43 to 84% and specificity up to 96%. Neuroimaging and AI technologies showed promising results in identifying early pathological changes and predicting PD onset. The highest specificity was achieved by neuromelanin-sensitive imaging model, while highest sensitivity was achieved by standard 10-s electrocardiogram (ECG) + Machine learning model.

CONCLUSION

Advanced diagnostic modalities such as AI-driven models and multimodal neuroimaging revealed promising results in early detection of prodromal PD. However, their clinical application as screening tool for prodromal PD is limited because of the lack of validation. Future research should be directed towards using Multimodal imaging in diagnosing and screening for prodromal PD.

CLINICAL TRIAL NUMBER

Not applicable.

Speech and language biomarkers for Parkinson's disease prediction, early diagnosis and progression

Parkinson's disease (PD), a multifaceted neurodegenerative disorder, can manifest as an array of motor and non-motor symptoms. Among these, speech and language impairments are particularly prevalent, often preceding motor dysfunctions. Emerging research indicates that these impairments may serve as early disease indicators. In this narrative review, we synthesised current findings on the potential of speech and language symptoms in PD identification and progression monitoring. Our review highlights convergent, albeit preliminary, lines of evidence supporting the value of speech-related features in detecting early or prodromal PD, even across language groups, especially with sophisticated analytical techniques. Distinct speech patterns in PD subtypes and other neurological disorders may assist in differential diagnosis and inform targeted management efforts. These features also evolve over the disease course and could effectively be utilised for disease tracking and guide management plan modifications. Advances in digital voice processing allow cost-effective, remote and scalable monitoring for larger populations.

Explaining facial action units' correlation with hypomimia and clinical scores in Parkinson's disease

This study aimed to identify facial regions characterizing hypomimia through facial action units (AU). It included video recordings from 109 early-stage Parkinson's disease (PD) and 45 healthy control (HC) subjects, performing rapid syllable repetitions. We identified the features contributing most to hypomimia by interpreting an XGBoost model classifying PD vs. HC. We evaluated the impact of biological sex and time on features and classification, and the correlation between model's predictions, AUs, and PD clinical scores over different times. The most discriminant AUs of hypomimia were found on the face lower part, independent of sex, and stable over time. Significant correlations were observed between AU17 (chin raiser) and rigidity of the upper left limb (r = - 0.4), as well as between AU9 (nose wrinkle) and neck rigidity (r = - 0.36). Correlations between XGBoost predictions and MDS-UPDRS3 and neck rigidity scores were also significant (r = 0.3). We obtained for PD detection an AUC of 79.8% and a balanced accuracy of 71.5%.

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.

A Systematic Review and Bayesian Meta-Analysis of Acoustic Measures of Prosody in Parkinson's Disease

PURPOSE

Linguistic prosody is affected in Parkinson's disease (PD), which implicates the basal ganglia's role in the production of prosody. However, there is no recent systematic synthesis of the available acoustic evidence of prosodic impairment in PD. This study aimed to identify the acoustic features of linguistic prosody that are consistently affected in PD.

METHOD

The authors systematically reviewed articles that reported acoustic features of prosodic production in PD. Articles focused on fundamental frequency (F0) and its variability, intensity and its variability, speech and articulation rate, and pause duration and ratio. From a total of 648 records identified, 36 met criteria for inclusion and exclusion. For each acoustic measurement and task, data from people with PD (PwPD) were compared with those from controls to extract effect sizes. Pooled effect sizes were estimated using robust Bayesian hierarchical regression models.

RESULTS

PD was associated with decreased F0 variability and increased pause duration. There was limited evidence of reduced intensity variability and speech rate in PwPD. No evidence was found to suggest that PD affects articulation rate or pause ratio.

CONCLUSIONS

The primary acoustic parameters of prosody affected by PD are F0 variability and pause duration. The identification of these acoustic parameters has important clinical implications for the selection of PD management strategies. The association of F0 variability and pause duration with PD suggests that the neural circuits controlling these parameters are at least partly shared and might include the basal ganglia. While the current study focused on the phonetic realization of prosodic cues, future studies should examine whether and how PD affects prosody at higher levels of processing.

SUPPLEMENTAL MATERIAL

https://doi.org/10.23641/asha.25892923.

The rise of Parkinson's disease is a global challenge, but efforts to tackle this must begin at a national level: a protocol for national digital screening and "eat, move, sleep" lifestyle interventions to prevent or slow the rise of non-communicable diseases in Thailand

The rising prevalence of Parkinson's disease (PD) globally presents a significant public health challenge for national healthcare systems, particularly in low-to-middle income countries, such as Thailand, which may have insufficient resources to meet these escalating healthcare needs. There are also many undiagnosed cases of early-stage PD, a period when therapeutic interventions would have the most value and least cost. The traditional "passive" approach, whereby clinicians wait for patients with symptomatic PD to seek treatment, is inadequate. Proactive, early identification of PD will allow timely therapeutic interventions, and digital health technologies can be scaled up in the identification and early diagnosis of cases. The Parkinson's disease risk survey (TCTR20231025005) aims to evaluate a digital population screening platform to identify undiagnosed PD cases in the Thai population. Recognizing the long prodromal phase of PD, the target demographic for screening is people aged ≥ 40 years, approximately 20 years before the usual emergence of motor symptoms. Thailand has a highly rated healthcare system with an established universal healthcare program for citizens, making it ideal for deploying a national screening program using digital technology. Designed by a multidisciplinary group of PD experts, the digital platform comprises a 20-item questionnaire about PD symptoms along with objective tests of eight digital markers: voice vowel, voice sentences, resting and postural tremor, alternate finger tapping, a "pinch-to-size" test, gait and balance, with performance recorded using a mobile application and smartphone's sensors. Machine learning tools use the collected data to identify subjects at risk of developing, or with early signs of, PD. This article describes the selection and validation of questionnaire items and digital markers, with results showing the chosen parameters and data analysis methods to be robust, reliable, and reproducible. This digital platform could serve as a model for similar screening strategies for other non-communicable diseases in Thailand.

Applied Machine Learning Techniques to Diagnose Voice-Affecting Conditions and Disorders: Systematic Literature Review

BACKGROUND

Normal voice production depends on the synchronized cooperation of multiple physiological systems, which makes the voice sensitive to changes. Any systematic, neurological, and aerodigestive distortion is prone to affect voice production through reduced cognitive, pulmonary, and muscular functionality. This sensitivity inspired using voice as a biomarker to examine disorders that affect the voice. Technological improvements and emerging machine learning (ML) technologies have enabled possibilities of extracting digital vocal features from the voice for automated diagnosis and monitoring systems.

OBJECTIVE

This study aims to summarize a comprehensive view of research on voice-affecting disorders that uses ML techniques for diagnosis and monitoring through voice samples where systematic conditions, nonlaryngeal aerodigestive disorders, and neurological disorders are specifically of interest.

METHODS

This systematic literature review (SLR) investigated the state of the art of voice-based diagnostic and monitoring systems with ML technologies, targeting voice-affecting disorders without direct relation to the voice box from the point of view of applied health technology. Through a comprehensive search string, studies published from 2012 to 2022 from the databases Scopus, PubMed, and Web of Science were scanned and collected for assessment. To minimize bias, retrieval of the relevant references in other studies in the field was ensured, and 2 authors assessed the collected studies. Low-quality studies were removed through a quality assessment and relevant data were extracted through summary tables for analysis. The articles were checked for similarities between author groups to prevent cumulative redundancy bias during the screening process, where only 1 article was included from the same author group.

RESULTS

In the analysis of the 145 included studies, support vector machines were the most utilized ML technique (51/145, 35.2%), with the most studied disease being Parkinson disease (PD; reported in 87/145, 60%, studies). After 2017, 16 additional voice-affecting disorders were examined, in contrast to the 3 investigated previously. Furthermore, an upsurge in the use of artificial neural network-based architectures was observed after 2017. Almost half of the included studies were published in last 2 years (2021 and 2022). A broad interest from many countries was observed. Notably, nearly one-half (n=75) of the studies relied on 10 distinct data sets, and 11/145 (7.6%) used demographic data as an input for ML models.

CONCLUSIONS

This SLR revealed considerable interest across multiple countries in using ML techniques for diagnosing and monitoring voice-affecting disorders, with PD being the most studied disorder. However, the review identified several gaps, including limited and unbalanced data set usage in studies, and a focus on diagnostic test rather than disorder-specific monitoring. Despite the limitations of being constrained by only peer-reviewed publications written in English, the SLR provides valuable insights into the current state of research on ML-based voice-affecting disorder diagnosis and monitoring and highlighting areas to address in future research.

Compensatory articulatory mechanisms preserve intelligibility in prodromal Parkinson's disease

INTRODUCTION

Dysarthria is highly prevalent in patients with Parkinson's disease (PD) and speech changes have already been detected in patients with prodromal PD on the acoustic level. However, the present study directly tracks underlying articulatory movements with electromagnetic articulography to investigate early speech alterations on the kinematic level in isolated REM sleep behavior disorder (iRBD) and compares them to PD and control speakers.

METHODS

Kinematic data of 23 control speakers, 22 speakers with iRBD, and 23 speakers with PD were collected. Amplitude, duration, and average speed of lower lip, tongue tip, and tongue body movements were analyzed. Naive listeners rated the intelligibility of all speakers.

RESULTS

Patients with iRBD produced tongue tip and tongue body movements that were larger in amplitude and longer in duration compared to control speakers, while remaining intelligible. Compared to patients with iRBD, patients with PD had smaller, longer and slower tongue tip and lower lip movements, accompanied by lower intelligibility. Thus, the data indicate that the lingual system is already affected in prodromal PD. Furthermore, lower lip and especially tongue tip movements slow down and speech intelligibility decreases if motor impairment is more pronounced.

CONCLUSION

Patients with iRBD adjust articulatory patterns to counteract incipient motor detriment on speech to maintain their intelligibility level.

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 integrated biometric voice and facial features for early detection of Parkinson's disease

Hypomimia and voice changes are soft signs preceding classical motor disability in patients with Parkinson's disease (PD). We aim to investigate whether an analysis of acoustic and facial expressions with machine-learning algorithms assist early identification of patients with PD. We recruited 371 participants, including a training cohort (112 PD patients during "on" phase, 111 controls) and a validation cohort (74 PD patients during "off" phase, 74 controls). All participants underwent a smartphone-based, simultaneous recording of voice and facial expressions, while reading an article. Nine different machine learning classifiers were applied. We observed that integrated facial and voice features could discriminate early-stage PD patients from controls with an area under the receiver operating characteristic (AUROC) diagnostic value of 0.85. In the validation cohort, the optimal diagnostic value (0.90) maintained. We concluded that integrated biometric features of voice and facial expressions could assist the identification of early-stage PD patients from aged controls.