Evaluating the Efficacy of a Self-administered Speech-Language App for People With Chronic, Nonfluent Aphasia: A Pilot Study
Bibliographic record
Abstract
Background Aphasia is a language deficit that is most often caused by stroke. Speech-language therapy is effective in helping people recover lost language, and it should lead to generalization to untrained tasks and gains in functional language. However, not everyone is able to receive therapy due to a lack of finances; a lack of insurance coverage; or, most recently, COVID-19. Objective This study has 3 aims. For aim 1, we investigated whether a person with moderate to severe aphasia could manage the setup of an app-based treatment independently. Our second aim was to evaluate whether conducting an intensive treatment without speech-language pathologist (SLP) involvement was feasible. Participants with aphasia were asked to use the app 2 hours per day for 10 days, and we were interested to see if they could maintain this regimen or if frustration or boredom would promote dropout. For the third aim, we determined whether participants with aphasia in our digital treatment would make the same kinds of language gains that they would if they were working with an SLP and whether treatment gains would generalize to other language modalities, indicating that neuroplastic changes occurred due to treatment. Methods Our pilot study used a single-subject design, with 3 participants experiencing nonfluent aphasia at least 1 year poststroke. Participants were trained to use a comprehension and production app, with instructions to use the app 2 hours per day for 10 days (total treatment time=20 hours). Multiple standardized assessments were taken at the following three time points: pretreatment, 1 week posttreatment, and 10 weeks posttreatment. A recording device was used to capture pretreatment and 10-week posttreatment at-home conversations between the participants with aphasia and the conversational partner. Results Data were variable among our 3 participants (P1, P2, and P3). P1 and P3 showed clinically significant improvements on several measurements of language; P2 did not. Aphasia severity also decreased in P1 and P3. The analysis of the discourse recorded in the home environments showed that P1 and P3 each made use of the app-trained words in spontaneous conversation (increase of >63%). All 3 participants with aphasia reported positive increases in quality of life, and all continued to use the app even after the treatment period ended. Conclusions Independently administered, intensive treatment had salubrious effects on 3 participants with aphasia. P2’s lack of improvement on language measures was attributed to not feeling challenged enough by the app. In general, the participants in this study were able to guide themselves in an independent manner to complete an intensive study, without using any SLP support. Though this study was only piloted on 3 individuals, it lays the groundwork for future studies assessing the independence of participants with aphasia in managing their own treatment. Conflicts of Interest None declared.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".