Speech-Language Pathologists (SLP) Treatment Methods and Approaches for Alzheimer's Dementia

Korytkowska, Marta; Obler, Loraine K.

doi:10.1044/persp1.sig2.122

Cited by 3 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The development of automated machine learning models that can learn the characteristics of MCI and provide an early and accurate identification of MCI is of utmost importance for two main reasons: First, an early identification can enable multidomain life style interventions and/or pharmacological treatments at the MCI stage, or even earlier, which can potentially delay or might even prevent the development of AD and other types of dementia ( 5 , 35 ). Second, the early identification, will provide time to patients and their families to make decisions about their care, family issues, and legal concerns ( 5 ).…”

Section: Introductionmentioning

confidence: 99%

Identification of Mild Cognitive Impairment From Speech in Swedish Using Deep Sequential Neural Networks

Themistocleous

Eckerström

Kokkinakis³

2018

Front. Neurol.

View full text Add to dashboard Cite

While people with mild cognitive impairment (MCI) portray noticeably incipient memory difficulty in remembering events and situations along with problems in decision making, planning, and finding their way in familiar environments, detailed neuropsychological assessments also indicate deficits in language performance. To this day, there is no cure for dementia but early-stage treatment can delay the progression of MCI; thus, the development of valid tools for identifying early cognitive changes is of great importance. In this study, we provide an automated machine learning method, using Deep Neural Network Architectures, that aims to identify MCI. Speech materials were obtained using a reading task during evaluation sessions, as part of the Gothenburg MCI research study. Measures of vowel duration, vowel formants (F1 to F5), and fundamental frequency were calculated from speech signals. To learn the acoustic characteristics associated with MCI vs. healthy controls, we have trained and evaluated ten Deep Neural Network Architectures and measured how accurately they can diagnose participants that are unknown to the model. We evaluated the models using two evaluation tasks: a 5-fold crossvalidation and by splitting the data into 90% training and 10% evaluation set. The findings suggest first, that the acoustic features provide significant information for the identification of MCI; second, the best Deep Neural Network Architectures can classify MCI and healthy controls with high classification accuracy (M = 83%); and third, the model has the potential to offer higher accuracy than 84% if trained with more data (cf., SD≈15%). The Deep Neural Network Architecture proposed here constitutes a method that contributes to the early diagnosis of cognitive decline, quantify the progression of the condition, and enable suitable therapeutics.

show abstract

Section: Introductionmentioning

confidence: 99%

Identification of Mild Cognitive Impairment From Speech in Swedish Using Deep Sequential Neural Networks

Themistocleous

Eckerström

Kokkinakis³

2018

Front. Neurol.

View full text Add to dashboard Cite

show abstract

Effects of Cued and Uncued Swallowing in Patients With Dementia

et al. 2022

View full text Add to dashboard Cite

Purpose: Parameters such as bolus location at swallow onset (BLSO), stage transition duration (STD), pharyngeal transition duration (PTD), pharyngeal response duration (PRD), and pharyngeal phase duration (PPD) often vary between cued and uncued swallowing conditions. Research has demonstrated that cued swallows may offer functional benefits that mitigate pathophysiological processes. However, there are limited data assessing differences between cued and uncued swallows in disordered populations, such as dementia. The purpose of this study was to evaluate if cued swallowing alters swallowing biomechanics in patients living with dementia. Method: Through a retrospective analysis of videofluoroscopic swallow studies (VFSS), 105 swallows from 26 participants living with dementia ( M age = 81 years; 14 women) were analyzed in duplicate by blinded raters using the Analysis of Swallowing Physiology, Events, Kinematics, and Timing method. Only VFSS with at least one cued and one uncued swallow were included in the analysis. Chi-square tests were used to explore differences in BLSO. Repeated-measures analyses of variance (ANOVAs) were used to explore differences in STD, PTD, PRD, and PPD. Results: Results revealed no significant differences in BLSO between cued and uncued swallows for patients living with dementia ( p = .934). Repeated-measures ANOVAs revealed no significant differences between the two types of swallows for STD ( p = .995), PTD ( p = .864), PRD ( p = .807), or PPD ( p = .660). Conclusions: This study suggests that there may be limited benefit to providing cued swallows to individuals living with dementia. Further research should investigate if this is due to impaired cognition and/or changes in motor control to volitionally complete the cued swallow.

show abstract

“Please Don't Assess Him to Destruction”: The R.A.I.S.E. Assessment Framework for Primary Progressive Aphasia

Cartwright

Volkmer

Whitworth

et al. 2023

Am J Speech Lang Pathol

View full text Add to dashboard Cite

Purpose: Speech-language pathologists (SLPs) assess people with primary progressive aphasia (PPA) through measurements of speech, language, communication, and well-being, with the aims of identifying challenges and strengths, monitoring change, and informing treatment directions and supports. The purpose of this clinical focus article is to highlight the necessity for person-centered assessment specific to PPA and to conceptualize a framework that acknowledges the multifaceted nature of assessment for this population. In this framework, the unique challenges posed by a diagnosis of PPA are addressed with the aim to provide practical guidance for clinicians and to support reflection on current practices. Method: In clinical and research practice, assessment of people with PPA requires an ever-evolving approach that is centered on the client. In this clinical focus article, a discussion-based consensus process was used to synthesize authentic longitudinal experiences of people with PPA to explore assessment approaches, tools, and philosophies. Results: This analysis of person-centered assessment identifies seven essential components of assessment in PPA that set the foundation for the five steps of the R.A.I.S.E. Assessment framework. These components each contribute to a clear definition of assessment that reveals clients' competencies with a strengths-based focus; prioritizes the reciprocity of benefits; promotes dynamic assessment; and recognizes the complexity, evolution of assessment over time, and advocacy. Conclusions: This clinical focus article takes a novel look at assessment in PPA by stepping away from assessment practices that focus on revealing deficits and decline and, instead, provides practical recommendations through the conceptualization of a PPA-specific assessment framework. The R.A.I.S.E. Assessment framework is grounded in principles of uplifting clients through person-centered assessment, keeps pace with best practice in PPA intervention, and contributes to a supportive experience for clients and families in the face of a progressive diagnosis over time.

show abstract

Speech-Language Pathologists (SLP) Treatment Methods and Approaches for Alzheimer's Dementia

Cited by 3 publications

References 28 publications

Identification of Mild Cognitive Impairment From Speech in Swedish Using Deep Sequential Neural Networks

Identification of Mild Cognitive Impairment From Speech in Swedish Using Deep Sequential Neural Networks

Effects of Cued and Uncued Swallowing in Patients With Dementia

“Please Don't Assess Him to Destruction”: The R.A.I.S.E. Assessment Framework for Primary Progressive Aphasia

Contact Info

Product

Resources

About