ObjectiveThe efficacy of spoken language comprehension therapies for persons with aphasia remains equivocal. We investigated the efficacy of a self-led therapy app, ‘Listen-In’, and examined the relation between brain structure and therapy response.MethodsA cross-over randomised repeated measures trial with five testing time points (12-week intervals), conducted at the university or participants' homes, captured baseline (T1), therapy (T2-T4) and maintenance (T5) effects. Participants with chronic poststroke aphasia and spoken language comprehension impairments completed consecutive Listen-In and standard care blocks (both 12 weeks with order randomised). Repeated measures analyses of variance compared change in spoken language comprehension on two co-primary outcomes over therapy versus standard care. Three structural MRI scans (T2-T4) for each participant (subgroup, n=25) were analysed using cross-sectional and longitudinal voxel-based morphometry.ResultsThirty-five participants completed, on average, 85 hours (IQR=70–100) of Listen-In (therapy first, n=18). The first study-specific co-primary outcome (Auditory Comprehension Test (ACT)) showed large and significant improvements for trained spoken words over therapy versus standard care (11%, Cohen’s d=1.12). Gains were largely maintained at 12 and 24 weeks. There were no therapy effects on the second standardised co-primary outcome (Comprehensive Aphasia Test: Spoken Words and Sentences). Change on ACT trained words was associated with volume of pretherapy right hemisphere white matter and post-therapy grey matter tissue density changes in bilateral temporal lobes.ConclusionsIndividuals with chronic aphasia can improve their spoken word comprehension many years after stroke. Results contribute to hemispheric debates implicating the right hemisphere in therapy-driven language recovery. Listen-In will soon be available on GooglePlay.Trial registration numberNCT02540889.

Highlights NUVA automatically assesses online word naming attempts in aphasia therapy. Significantly more accurate and faster than leading commercial speech recognition. Accuracies between 83.6% and 93.6% validate use in clinical research.

Anomia (word finding difficulties) is the hallmark of aphasia an acquired language disorder, most commonly caused by stroke. Assessment of speech performance using pijcture naming tasks is therefore a key method for identification of the disorder and monitoring patient's response to treatment interventions. Currently, this assessment is conducted manually by speech and language therapists (SLT). Surprisingly, despite advancements in ASR and artificial intelligence with technologies like deep learning, research on developing automated systems for this task has been scarce. Here we present an utterance verification system incorporating a deep learning element that classifies 'correct'/'incorrect' naming attempts from aphasic stroke patients. When tested on 8 native British-English speaking aphasics the system's performance accuracy ranged between 83.6% to 93.6%, with a 10 fold cross validation mean of 89.5%. This performance was not only significantly better than one of the leading commercially available ASRs (Google speech-to-text service) but also comparable in some instances with two independent SLT ratings for the same dataset.

Background iReadMore is a digital therapy for people with acquired reading impairments (known as alexia) caused by brain injury or neurodegeneration. A phase II clinical trial demonstrated the efficacy of the digital therapy research prototype for improving reading speed and accuracy in people with poststroke aphasia (acquired language impairment) and alexia. However, it also highlighted the complexities and barriers to delivering self-managed therapies at home. Therefore, in order to translate the positive study results into real-world benefits, iReadMore required subsequent design innovation. Here, we present qualitative findings from the co-design process as well as the methodology. Objective We aimed to present a methodology for inclusive co-design in the redesign of a digital therapy prototype, focusing on elements of accessibility and user engagement. We used framework analysis to explore the themes of the communications and interactions from the co-design process. Methods This study included 2 stages. In the first stage, 5 in-person co-design sessions were held with participants living with poststroke aphasia (n=22) and their carers (n=3), and in the second stage, remote one-to-one beta-testing sessions were held with participants with aphasia (n=20) and their carers (n=5) to test and refine the final design. Data collection included video recordings of the co-design sessions in addition to participants’ written notes and drawings. Framework analysis was used to identify themes within the data relevant to the design of digital aphasia therapies in general. Results From a qualitative framework analysis of the data generated in the co-design process, 7 key areas of consideration for digital aphasia therapies have been proposed and discussed in context. The themes generated were agency, intuitive design, motivation, personal trajectory, recognizable and relatable content, social and sharing, and widening participation. This study enabled the deployment of the iReadMore app in an accessible and engaging format. Conclusions Co-design is a valuable strategy for innovating beyond traditional therapy designs to utilize what is achievable with technology-based therapies in user-centered design. The co-designed iReadMore app has been publicly released for use in the rehabilitation of acquired reading impairments. This paper details the co-design process for the iReadMore therapy app and provides a methodology for how inclusive co-design can be conducted with people with aphasia. The findings of the framework analysis offer insights into design considerations for digital therapies that are important to people living with aphasia.

No abstract