Identification of dysarthria types based on perceptual analysis

Zyski, Barbara Jean; Weisiger, Bradford E.

doi:10.1016/0021-9924(87)90025-6

Cited by 80 publications

(46 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performance of residents and speech therapists was equally disappointing. Zyski and Weisiger [15] found better scores: in their study, speech/language pathologists correctly identified dysarthria type in approximately 50% of all cases. However, assessment in their study was more structured as their raters used an adapted checklist with 16 perceptual dimensions of the original 38 dimensions of the Mayo Clinic rating system for analysis.…”

Section: Discussionmentioning

confidence: 99%

“…In addition, we examined whether there was any difference between groups of raters and whether clinical information on each patient would improve the score of each rater. Based on the results of Zyski and Weisiger [15], we presumed raters to correctly diagnose dysarthrias in 50% of all cases. We defined a difference of 25% or more between groups of raters as clinically relevant.…”

Section: Methodsmentioning

confidence: 99%

“…Despite the fact that this system is the one most widely used, it is also recognized that increasing knowledge of clinicoanatomic relations in the era of sophisticated brain imaging may lead to an adaptation and/or refinement of the system [12]. There are 3 studies on rater reliability of the Mayo Clinic’s rating system [13,14,15]. Zyski and Weisiger [15 ]included speech/language pathologists (specialists and graduate students) as raters.…”

Section: Introductionmentioning

confidence: 99%

“…There are 3 studies on rater reliability of the Mayo Clinic’s rating system [13,14,15]. Zyski and Weisiger [15 ]included speech/language pathologists (specialists and graduate students) as raters. They showed that approximately 50% of all raters did not correctly identify the dysarthria type.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Clinical Identification of Dysarthria Types among Neurologists, Residents in Neurology and Speech Therapists

Graaff¹,

Kuiper²,

Zwinderman

et al. 2009

Eur Neurol

View full text Add to dashboard Cite

Background: Classification of dysarthria types comprises flaccid, spastic, ataxic, hypo- and hyperkinetic and mixed dysarthria. This study focussed on the ability of neurologists to clinically identify the correct type of dysarthria in neurological patients. Methods: Eighteen patients with dysarthria and 4 healthy controls were enrolled in the study. The gold standard for dysarthria type was the underlying neurological disease. Recordings of a standard reading passage and free speech were made. Raters were neurologists, residents in neurology and speech therapists, whose scores were compared. Results: Neurologists correctly identified 40% of the recordings, residents 41%, and speech therapists 37%. Interrater agreement was fair among all 3 groups; intrarater agreement was fair to moderate. Conclusion: This study suggests that neurologists should be aware of the unreliability of identifying the dysarthria type without the use of additional validated instruments or rating scales in a clinical setting.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Clinical Identification of Dysarthria Types among Neurologists, Residents in Neurology and Speech Therapists

Graaff¹,

Kuiper²,

Zwinderman

et al. 2009

Eur Neurol

View full text Add to dashboard Cite

show abstract

“…Perceptual ratings and acoustic analyses of speech deficits do not allow valid inferences on the kinematic characteristics of articulation disorders in terms of the duration, displacement, and velocity of orofacial gestures [17]. Therefore, movement analysis systems are required to corroborate the suggestion of restricted range of articulatory movements and reduced peak velocity.…”

Section: Introductionmentioning

confidence: 99%

Speech Disorders following Severe Traumatic Brain Injury: Kinematic Analysis of Syllable Repetitions Using Electromagnetic Articulography

Jaeger

Hertrich

Stattrop

et al. 2000

Folia Phoniatr Logop

View full text Add to dashboard Cite

Using electromagnetic articulography, the lips, the tip of the tongue, and the tongue dorsum were tracked during repetitions of the syllables [pa], [ta] and [ka] in 10 speakers with dysarthria following severe traumatic brain injury and in 10 age-matched control subjects. When asked to produce the syllable trains as fast as possible, the patient group showed a rather homogeneous pattern of movement abnormalities including prolonged syllable durations and reduced peak velocity/amplitude ratios. Most presumably, limited speed generation gives rise to the impaired ability to increase speech rate. During the habitual speaking condition, reduced velocity/amplitude ratios were restricted to the tongue tip and tongue dorsum. Obviously, the tongue and the lips are differentially affected in dysarthria following severe traumatic brain injury.

show abstract

Artificial Intelligence‐Powered Acoustic Analysis System for Dysarthria Severity Assessment

Zhang,

Shang,

Yang

et al. 2023

Advanced Intelligent Systems

View full text Add to dashboard Cite

Dysarthria is common in movement disorders, such as Wilson's disease (WD), Parkinson's disease, or Huntington's disease. Dysarthria severity assessment is often indispensable for the management of these diseases. However, such assessment is usually labor‐intensive, time‐consuming, and expensive. To seek efficient and cost‐effective solutions for dysarthria assessment, an artificial intelligence (AI)‐powered acoustic analysis system is proposed and its performance in a valuable sample of WD, an ideal disease model with mainly mixed dysarthria, is verified. A test‐retest reliability analysis yields excellent reproducibility in the acoustic measures (mean intraclass correlation coefficient [ICC] = 0.81). Then, a system for dysarthria assessment is trained with WD patients (n = 65) and sex‐matched healthy controls (n = 65) using a machine learning approach. The system achieves reasonable performance in evaluating dysarthria severity with either stepwise classification or regression (all areas under the curve >80%; mean absolute error = 6.25, r = 0.79, p < 0.0001). The diadochokinesis and sustained phonation tasks contribute the most to prediction, and the corresponding acoustic features can provide significant and independent contributions. The present study demonstrates the feasibility and good performance of the AI‐powered acoustic analysis framework, offering the potential to facilitate early screening and subsequent management of dysarthria.

show abstract

Identification of dysarthria types based on perceptual analysis

Cited by 80 publications

References 23 publications

Clinical Identification of Dysarthria Types among Neurologists, Residents in Neurology and Speech Therapists

Clinical Identification of Dysarthria Types among Neurologists, Residents in Neurology and Speech Therapists

Speech Disorders following Severe Traumatic Brain Injury: Kinematic Analysis of Syllable Repetitions Using Electromagnetic Articulography

Artificial Intelligence‐Powered Acoustic Analysis System for Dysarthria Severity Assessment

Contact Info

Product

Resources

About