Search

Background: Dementia is a cognitive decline that leads to the progressive deterioration of an individual's ability to perform daily activities independently. As a result, a considerable amount of time and resources are spent on caretaking. Early detection of dementia can significantly reduce the effort and resources needed for caretaking. Aims: This research proposes an approach for assessing cognitive decline by analysing speech data, specifically focusing on speech relevance as a crucial indicator for memory recall. Methods & Procedures: This is a cross‐sectional, online, self‐administered. The proposed method used deep learning architecture based on transformers, with BERT (Bidirectional Encoder Representations from Transformers) and Sentence‐Transformer to derive encoded representations of speech transcripts. These representations provide contextually descriptive information that is used to analyse the relevance of sentences in their respective contexts. The encoded information is then compared using cosine similarity metrics to measure the relevance of uttered sequences of sentences. The study uses the Pitt Corpus Dementia dataset for experimentation, which consists of speech data from individuals with and without dementia. The accuracy of the proposed multi‐QA‐MPNet (Multi‐Query Maximum Inner Product Search Pretraining) model is compared with other pretrained transformer models of Sentence‐Transformer. Outcomes & Results: The results show that the proposed approach outperforms the other models in capturing context level information, particularly semantic memory. Additionally, the study explores the suitability of different similarity measures to evaluate the relevance of uttered sequences of sentences. The experimentation reveals that cosine similarity is the most appropriate measure for this task. Conclusions & Implications: This finding has significant implications for the early warning signs of dementia, as it suggests that cosine similarity metrics can effectively capture the semantic relevance of spoken language. The persistent cognitive decline over time acts as one of the indicators for prevalence of dementia. Additionally early dementia could be recognised by analysis on other modalities like speech and brain images. WHAT THIS PAPER ADDS: What is already known on this subject: It is already known that speech‐ and language‐based detection methods can be useful for dementia diagnosis, as language difficulties are often early signs of the disease. Additionally, deep learning algorithms have shown promise in detecting and diagnosing dementia through analysing large datasets, particularly in speech‐ and language‐based detection methods. However, further research is needed to validate the performance of these algorithms on larger and more diverse datasets and to address potential biases and limitations. What this paper adds to existing knowledge: This study presents a unique and effective approach for cognitive decline assessment through analysing speech data. The study provides valuable insights into the importance of context and semantic memory in accurately detecting the potential in dementia and demonstrates the applicability of deep learning models for this purpose. The findings of this study have important clinical implications and can inform future research and development in the field of dementia detection and care. What are the potential or actual clinical implications of this work?: The proposed approach for cognitive decline assessment using speech data and deep learning models has significant clinical implications. It has the potential to improve the accuracy and efficiency of dementia diagnosis, leading to earlier detection and more effective treatments, which can improve patient outcomes and quality of life. [ABSTRACT FROM AUTHOR]

Background: Research is beginning to shed light on the practices employed by speech‐language therapists (SLTs) for the management of acquired dysarthria. However, studies that explore SLTs' satisfaction with the effectiveness of current therapies and their interest in new treatment methods for this population have not been carried out. One potential new method is neuromuscular electrical stimulation (NMES): the pool of evidence for its use in rehabilitation is increasing, yet it has not been widely explored for use with dysarthria. Aim: To extend the understanding of acquired dysarthria management practices employed by SLTs across the globe and determine their satisfaction with current therapy options. To explore their interest in using NMES with this population. Methods and Procedures: A cross‐sectional international online survey was developed and disseminated to SLTs working with adults with acquired dysarthria through international professional associations. The survey collected information on demographic characteristics, dysarthria management practices, satisfaction with treatment effectiveness and interest in and knowledge of NMES. Survey responses were analysed using descriptive and inferential statistics, and quantitative content analysis. Outcomes and Results: A total of 211 SLTs (North America, 48.8%; Europe, 36%; Asia, 8.1%; Oceania, 5.7%; Africa, 0.9%; South America, 0.5%) completed the survey in full. Management practices varied considerably. There was a clear preference for informal assessments, mainly oral‐motor examinations, focusing on body functions and structures. The majority of respondents rejected the use of non‐speech oral motor exercises as a clinical or carryover exercise. Variable satisfaction with current speech subsystem treatments was noted; however, overall, there was a general dissatisfaction. Whilst a strong interest in the use of NMES for dysarthria was evidenced, it was noted that most SLTs lacked fundamental knowledge of NMES principles and application. Conclusion: SLTs' management practices and satisfaction with acquired dysarthria treatments differed substantially. Investigations of the potential use of NMES for dysarthria treatment are of interest. WHAT THIS PAPER ADDS: What is already known on the subject: Recent country‐specific surveys have explored speech‐language therapists' (SLTs') assessment and intervention practices for acquired dysarthria. These studies indicate that although clinical management for this speech disorder mainly involves informal assessment tools and impairment‐focused treatment, communication beyond the impairment, such as the activity and participation domains, is also frequently assessed and treated. What this paper adds to existing knowledge: The majority of SLTs are dissatisfied with the overall benefits of current acquired dysarthria treatment. Phonatory, respiration and speech rate therapies are perceived to be more effective than prosody, articulation and resonance treatments. Despite a general lack of theoretical knowledge, most SLTs are interested in neuromuscular electrical stimulation treatment for acquired dysarthria. What are the potential or actual clinical implications of this work?: New, evidence‐based treatments are needed for SLTs to be confident in the effectiveness of their acquired dysarthria treatment. [ABSTRACT FROM AUTHOR]

Background: During the COVID‐19 pandemic, Ireland implemented a series of stringent public health measures, including lockdowns and suspension of non‐urgent clinical services. Aims: To investigate the impact of the COVID‐19 pandemic on the demand for and delivery of speech and language therapy (SLT) services in Ireland in 2020. Methods & Procedures: Two iterations of a cross‐sectional, mixed‐methods online survey were distributed to speech and language therapists (SLTs) and SLT students in Ireland in the spring and autumn of 2020 using a combination of purposive and snowball sampling. The spring survey yielded 407 responses (including 14 from SLT students), while 197 respondents took part in the autumn (13 students). Survey analysis focused on questions related to the impact of the COVID‐19 pandemic on delivery and demand for SLT services (student responses were excluded from analysis owing to low response rate). The largest group in respect of experience were senior SLTs (58% in both surveys). The work settings most strongly represented were HSE primary care (34.4%) and disability services (26.5%) in the spring, and HSE primary care (39.1%), acute hospitals (22.8%) and disability services (20.8%) in the autumn. We used descriptive statistics, including distribution analysis, to analyse the quantitative data. Free text data were interrogated through a variant of a conventional qualitative content analysis. Outcomes & Results: In the spring, cessation of face‐to‐face services featured prominently (reported by 65.6% versus 14.2% in the autumn), across SLTs' work settings, except acute hospitals. Lower demand was reported by 42.5% in the spring, while in the autumn, 48.7% indicated that demand was higher. SLTs experienced large‐scale redeployment (spring: 45.9%, autumn: 38.4%), with HSE primary care SLTs redeployed most (spring: 71.7%; autumn: 62.3%). The need to suddenly pivot to telehealth was a significant challenge in terms of training, technology and logistics. New ways of working emerged and gradually, telehealth became more embedded. SLTs also had to adapt to working with evolving public health measures, such as space restrictions and personal protective equipment (PPE) requirements. Across the two survey iterations, SLTs reported tensions between demands and capacity: while referrals and demand initially decreased in the spring, this led to increased backlog and longer waiting lists, ongoing and increasing pressure on clinicians and services, and negatively impacted clients and families. Conclusions & Implications: The COVID‐19 pandemic had a significant negative impact on SLT services in Ireland. Going forward, the SLT profession and its services will require sustained support to mitigate long‐term negative consequences, such as increased waiting lists. WHAT THIS PAPER ADDS: What is already known on this subject: The negative impact of the COVID‐19 pandemic on SLT services has been examined in several countries. Ireland imposed more stringent pandemic‐management measures than many other countries, and it was therefore warranted to investigate how SLT services in the country were affected. What this study adds to the existing knowledge: Face‐to‐face SLT services effectively ceased in most non‐urgent contexts in spring 2020. This coincided with large‐scale redeployment of SLTs to non‐SLT contexts. By autumn 2020, demand had increased again, but not all services had recommenced, and redeployment was still a factor. Although SLTs adapted to the ongoing changes imposed by the pandemic, they voiced concern about increasing backlogs and longer waiting lists, ongoing and increasing pressure on both SLTs and services, and negative impacts on clients and families. What are the actual and clinical implications of this work?: The COVID‐19 pandemic had a significant negative impact on SLT services in Ireland. Going forward, the SLT profession and its services will require sustained support to mitigate long‐term negative consequences, such as increased waiting lists. [ABSTRACT FROM AUTHOR]

Background: Supporting psychosocial well‐being in aphasia is necessarily person‐centred, interdisciplinary and coordinated. Shortcomings in such support are described in Ireland and elsewhere. Speech and language therapists (SLTs) are integral; and describing current practice and barriers they experience is important for enhancing service delivery. Aims: To understand how SLTs enact, and are supported to enact, aphasia psychosocial care in Ireland. Methods & Procedures: This is a cross‐sectional, online, self‐administered clinician survey targeting SLTs working minimally 1 year post‐qualification with persons with aphasia of any aetiology in Ireland. The survey questions were charted against key constructs of the implementation science framework, normalization process theory (NPT), and descriptive statistics were applied. Outcomes & Results: A total of 54 eligible datasets were included. SLTs believed psychosocial support to be part of their role, but perceived multiple barriers in enacting it. These included a lack of training, clinical supervision, management support, role recognition, and access to and joint working with mental health professionals and services. Conclusions & Implications: SLTs in Ireland face a range of individual and structural barriers, including care coordination and resourcing. There is a clear need not only for training, upskilling and mentorship, but also for wider changes around access to mental health professionals and clarity around the processes of referral, coordination and integration of aphasia care across settings. These findings comprise preliminary insights into current practices. Further research is needed as well as clarity on best‐practice pathways for different aetiologies of aphasia. Articulating current practices using NPT may have utility for developing empirically informed and principled interventions to improve service delivery. WHAT THIS PAPER ADDS: What is already known on this subject: People with aphasia of all aetiologies are at risk of psychosocial problems. Shortcomings in access and the availability of appropriate support have been documented both internationally and in Ireland. To address this issue, an important first step is to understand how SLTs in Ireland currently enact and are supported to enact aphasia psychosocial care. What this study adds to the existing knowledge: The findings describe the potential levers and barriers to progressing aphasia psychosocial care in Ireland. A range of individual, team and structural factors were identified. These were locally contextualized but similar issues are reported in other countries. Linking attitudes with NPT constructs provides a first step for further principled implementation projects. What are the practical and clinical implications of this study?: Addressing psychosocial problems is perceived as a legitimate part of the speech and language therapy role. SLTs in Ireland enact a range of therapeutic approaches but may need opportunities for formal training and supervision, and for better coordination and integration with other mental health services and disciplines. Understanding differences in care pathways across the range of aphasia aetiologies is additionally important given the emphasis on post‐stroke aphasia in the literature. [ABSTRACT FROM AUTHOR]