Search

Background: Evidence should guide decisions in aphasia practice across the continuum of stroke care; however, evidence–practice gaps persist. This is particularly pertinent in the acute setting where 30% of people with stroke will have aphasia, and speech pathologists experience many challenges implementing evidence‐based practice. This has important consequences for people with aphasia and their close others, as well as speech pathologists working in acute settings. Aims: This study protocol details how we will target practice change using a behavioural approach, with the aim of promoting the uptake of synthesized evidence in aphasia management post‐stroke in the acute hospital setting. Methods & Procedures: We will conduct a mixed‐methods before‐and‐after study following the Knowledge‐to‐Action (KTA) framework. Researchers, speech pathologists and people with lived experience of aphasia will collaborate to identify and prioritize practice gaps, and develop and implement changes to clinical practice based on the Theoretical Domains Framework and Behaviour Change Wheel. Discussion: This study may provide a template for acute stroke services in how to use an implementation science approach to promote the application of synthesized evidence into routine clinical practice to ensure people with aphasia receive high‐quality services. Collaboration among researchers, healthcare providers, people with aphasia and their close others ensures that the identification and targeting of practice gaps are driven by theory, lived experience and the local context. WHAT THIS PAPER ADDS: What is already known on this subject: Synthesized evidence, such as clinical guidelines and consensus statements, provides the highest level of evidence to inform clinical practice, yet discrepancies between delivered care and evidence remain. This discrepancy is of note in the acute setting where clinicians report many challenges implementing the best available evidence, combined with a high proportion of people with stroke who will have aphasia (30%). There are many reasons why evidence is not put into practice, and efforts to change clinical practice need to consider these barriers when developing interventions. What this paper adds to existing knowledge: This study protocol details an implementation science approach to affect clinical practice change, informed by a collaboration of key stakeholders (researchers, speech pathologists, and people with aphasia and their close others). Protocol papers that focus on bridging the gap between evidence and practice are uncommon in communication disorders; moreover, explicit prioritization of practice gaps is a critical but often overlooked aspect of promoting evidence‐based practice. What are the potential or actual clinical implications of this work?: This protocol provides insights into how one study site identified and prioritized evidence–practice gaps using a participatory approach. We provide insights into how clinical practice change may occur by describing how we plan to identify priority evidence–practice gaps and develop an intervention to improve the use of aphasia evidence in routine practice. This protocol aims to share an implementation science approach to service improvement that may be replicated across other services. [ABSTRACT FROM AUTHOR]

In this paper, automatic assessment models are developed for two perceptual variables: speech intelligibility and voice quality. The models are developed and tested on a corpus of Dutch tracheoesophageal (TE) speakers. In this corpus, each speaker read a text passage of approximately 300 syllables and two speech therapists provided consensus scores for the two perceptual variables. Model accuracy and stability are investigated as a function of the amount of speech that is made available for speaker assessment (clinical setting). Five sets of automatically generated acoustic-phonetic speaker features are employed as model inputs. In Part I, models taking complete feature sets as inputs are compared to models taking only the features which are expected to have sufficient support in the speech available for assessment. In Part II, the impact of phonetic content and stimulus length on the computer-generated scores is investigated. Our general finding is that a text encompassing circa 100 syllables is long enough to achieve close to asymptotic accuracy. [ABSTRACT FROM AUTHOR]