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

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.

show abstract

“…Combined: 20 [ 49 , 51 , 53 , 60 , 65 , 66 , 71 , 73 , 98 , 101 , 118 , 123 , 125 , 133 , 134 , 171 , 180 , 181 , 185 , 188 ]…”

Section: Resultsunclassified

“…Combined: 45 [ 42 , 44 , 48 , 51 , 52 , 54 , 57 , 62 , 63 , 67 – 70 , 72 , 74 , 76 , 79 , 81 , 85 , 86 , 89 – 91 , 93 , 94 , 96 , 97 , 99 , 100 , 119 , 120 , 122 , 124 , 126 – 131 , 134 , 135 , 170 , 171 , 184 , 192 ]…”

Section: Resultsunclassified

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

Idrisoglu¹,

Dallora²,

Anderberg³

et al. 2023

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…The results identified an AUROC of 0.86 in men and 0.93 in women for discriminating PD patients from controls, which diagnostic performance is similar with our results. Furthermore, speech features combined with support vector machine classifier assisted detection of early-stage PD from controls with an accuracy of 89% in men and 70% in women, and provided an accuracy of 63% for detecting participants with REM-stage sleep behavior disorders (RBD) from controls 18 . These results combined with our findings support a recent multi-center European study that simple speech recordings with automatic speech analysis and machine learning classifier could serve as sensitive noninvasive early biomarkers for PD and those with the PD prodromal symptom of RBD 19 .…”

Section: Discussionmentioning

confidence: 99%

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

Lim

Chiu

et al. 2022

npj Parkinsons Dis.

View full text Add to dashboard Cite

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.

show abstract

“…Previous studies investigated the speech production in iRBD patients on the acoustic level. A reduced ability to modulate pitch was observed in speakers with iRBD [4][5][6] : Besides monopitch, articulatory deficits were reported most dominant 7 leading to a reduction of the acoustic vowel space was determined 8 as well as a trend towards lower articulation rates 5 . While acoustic speech parameters deviated between speakers with iRBD and a control group, no perceptual differences were identified by listeners 5 .…”

Section: Introductionmentioning

confidence: 96%

Compensatory mechanisms enables intelligibility in prodromal Parkinson’s disease

Thies

Mücke

Geerts

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Speech impairment is already present on the acoustic level in speakers with isolated rapid eye movement sleep behavior disorder (iRBD). The aim of this study was to determine whether speech changes are already present on the articulatory level and if how these differ from healthy control speakers and speakers with Parkinson's disease (PD). Methods: Kinematic data were collected from 68 age and sex-matched subjects: healthy control speakers (n=23), patients with iRBD (n=22), and patients with PD (n=23). All participants were recorded with electromagnetic articulography (AG 501) to capture articulatory movements of the lower lip, the tongue tip and the tongue body. Movement amplitudes, durations and average speeds were calculated per articulator. In addition, naive listeners rated the intelligibility of the speech sampled produced by the participants. Results: The results of the production experiment indicate changes between the control and the iRBD group as well as between the iRBD and the PD group. Movement durations increase from the control group to the iRBD group and further to the PD group. In contrary, movement amplitudes increase in prodromal PD and decreased from PD onwards. This relationship was reflected by preserved articulatory speed in iRBD patients, but articulatory slowdown in PD. Intelligibility is lower in speakers with PD, but does not differ between the control and the iRBD group. Conclusion: Speakers with iRBD adjust underlying articulatory movement patterns to maintain their intelligibility level.

show abstract

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

Cited by 24 publications

References 29 publications

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

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

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

Compensatory mechanisms enables intelligibility in prodromal Parkinson’s disease

Contact Info

Product

Resources

About