CoChat

Outcomes of an App-Based Intervention to Target Naming Among Individuals With Poststroke Aphasia: Virtual Randomized Controlled Trial

Open access

The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index; 11 of the 30 sources its claims cite were checked for support.

Abstract

Background: People with aphasia present with language and communication deficits, most notably in lexical retrieval (naming). Although positive outcomes in naming have been observed following speech-language treatment, many individuals with aphasia continue to face impairments after the acute phase of rehabilitation. Mobile app-based therapies are increasingly being used by speech-language pathologists in the rehabilitation of people with aphasia as an adjunct to or in lieu of traditional in-person therapy approaches. These apps can increase the intensity of treatment and have been shown to result in meaningful outcomes across several domains. Objective: VoiceAdapt is a mobile therapy app addressing naming impairments, designed within a user-centered design framework. The VoiceAdapt app uses two evidence-based lexical retrieval treatments to engage people with aphasia to improve their naming abilities through interaction with the app. The purpose of this study was to conduct a randomized controlled trial to examine the preliminary clinical efficacy of training with VoiceAdapt on the language and communication outcomes of people with aphasia. Methods: A two-arm, waitlist-controlled, crossover group randomized controlled trial was conducted at two sites within Canada. During the intervention phase, participants completed 5 weeks of independent training with the app, which involved naming practice using Semantic Features Analysis and Phonological Components Analysis. The primary outcome measure was naming performance (Boston Naming Test); secondary outcomes included measures of overall language and naming (Western Aphasia Battery-Revised), communication (Communication Effectiveness Index), and quality of life (Stroke and Aphasia Quality of Life Scale-39). Results: A total of 37 people with aphasia in the chronic stages (average 4.6 y postonset of aphasia) participated in this study. Participants used the app for an average of 20 hours over the 5-week intervention phase. Training with VoiceAdapt resulted in an increase of 1.6 points on the Boston Naming Test (Cohen d=0.3). Evidence for improved naming was also observed on trained items, as well as subtests of naming or word-finding on the WAB-R. Training with the app also resulted in a significant increase in participants' perceptions of their communication quality of life (increase of 0.1 points; Cohen d=0.3), but no other measures (WAB-R Aphasia Quotient, Communicative Effectiveness Index) were significant. Conclusions: Individuals with aphasia who used the VoiceAdapt app for 5 weeks to target naming skills demonstrated measurable gains in naming and communication-based quality of life. Notably, these changes were observed in a remotely delivered program, in participants who were in the chronic stages of aphasia. These findings inform the profession on the use of app-based home therapy programs as an accessible, cost-effective option for individuals in the chronic stages of recovery who often have limited options for rehabilitation.

Overview

CoChat Summary

TL;DR

In a two-site virtual randomized waitlist-controlled crossover trial, 5 weeks of self-directed naming practice with the VoiceAdapt app produced small but measurable gains in naming and communication-related quality of life among 37 people with chronic poststroke aphasia. The trial ended early after interim analyses and slower-than-expected recruitment.

Key findings

  • On the primary outcome, Boston Naming Test performance increased by 1.6 points with VoiceAdapt training (95% credible interval −0.3 to 3.6; Cohen d=0.3; posterior probability >0 = 0.954).
  • Naming-related secondary measures also improved: WAB-R Object Naming increased by 3 points (95% CI 1-5; d=0.4), WAB-R Naming and Word Finding increased by 2.6 points (95% CI 0.15-5; d=0.3), and the 322-item Study Stimulus Naming Test increased by 13 points (95% CI 7-19; d=0.9).
  • SAQOL-39g Communication Quality of Life increased by 0.1 points (d=0.3), but no significant effects were found for WAB-R Aphasia Quotient (0.4; d=0.01), overall SAQOL-39g (decrease of 0.01 points; d=0.1), CETI-participant (−5; d=0.1), or CETI-partner (0.1; d=0.2).
  • Participants used the app for an average of 19.5 (SD 8.6) hours over the 5-week intervention; mean System Usability Scale score was 61.2 (SD 18.9).

Methods

  • Two-arm, waitlist-controlled, crossover group randomized controlled trial conducted at two Canadian sites; all procedures were delivered virtually due to COVID-19.
  • 38 participants with chronic aphasia were randomized, and 37 completed both phases; participants averaged 62.2 (SD 13.9) years of age and 4.6 (SD 4.2) years postonset.
  • Intervention was 5 weeks of independent tablet-based naming practice using Semantic Features Analysis and Phonological Components Analysis, targeted at 1 hour per weekday for 25 total hours.
  • Outcomes were analyzed with Bayesian mixed-effects regression; primary outcome was the Boston Naming Test, with secondary measures including WAB-R, CETI, and SAQOL-39g.

Limitations

  • The paper states that COVID-19 necessitated virtual delivery, which may have affected recruitment and resulted in a smaller-than-planned sample; participants also did not practice the full prescribed dosage.
  • The paper states there was no maintenance assessment for all participants postintervention, only one maintenance assessment at approximately 6 weeks for the treatment condition, and participants could not be blinded to condition, though assessors were blinded.
  • Evident from the text: the trial ended early after interim analyses and slow recruitment; one participant withdrew due to frustrations with automatic speech recognition, and the app’s ASR was noted as not always accurate. The sample excluded severe aphasia and included only mild-to-moderate chronic aphasia, limiting generalizability.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.2196/67711

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1. Study design.
Figure 1. Study design.CC BY · PubMed Central
Figure 2. Participant flowchart.
Figure 2. Participant flowchart.CC BY · PubMed Central

Verification

Claims the paper makes

8 Valid · 1 Not valid · 14 Not checked · 56 Own results and interpretations

26 more claims

Create a free account to see all 79 claims and every source verdict.

See all claims — free account
  • Probably not a substantial claim. 35
  • It may state two separate claims as one. 19
  • The quote only partly states this claim. 3
  • Borderline: one of the tests for a substantial claim is unclear. 1

Create a free account to see these claims.

Citations

Cites

Show all 54 references

Research works printed but not linked: 4

  1. Ali, Predictors of poststroke aphasia recovery, Stroke, 10.1161/STROKEAHA.120.03116 · doi:10.1161/strokeaha.120.03116
  2. Griffel, Aphasie Verwandte Geb, 46, 6
  3. Goodglass H Kaplan E Weintraub S . Boston Naming Test. Lea & Febiger; 1983. URL: https://psycnet.apa.org/doiLanding?doi=10.1037%2Ft27208-000 [Accessed 11-08-2025] · DOI
  4. Brooke J . SUS: a “quick and dirty” usability scale. In: Jordan PW Thomas B Weerdmeester BA McLelland IL , editors. Usability Evaluation In Industry. Taylor and Francis; 1996:189-194.

Cited by

See all 2

Metadata

Authors
Kim, E. S., Laird, L., Wilson, C., Stewart, S., Mildner, P., Möller, S., Schatz, R., Spang, R. P., Voigt-Antons, J.-N., & Rochon, E.
Affiliations
  • University of Alberta (CA)
  • University Health Network (CA)
  • Technische Universität Berlin (DE)
  • AIT Austrian Institute of Technology GmbH (AT)
Corresponding author
Kim, Esther S
Venue
JMIR mHealth and uHealth
Published
2025-08-18
Volume
13
Pages
e67711-e67711
ISSN
2291-5222 (ISSN-L)
OpenAlex
W4414300929
Cited by
2
References
54
Citations by year
2026: 2
FWCI
1.13
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • JMIR mhealth and uhealth (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • PubMed Central (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Neurobiology of Language and Bilingualism
  • Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
  • Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
Keywords
post-stroke aphasia, naming impairment, word retrieval, chronic stroke, Boston Naming Test, Western Aphasia Battery-Revised, user-centered design
MeSH terms
Stroke Rehabilitation, Adult, Aged, Aphasia, Canada, Female, Humans, Language Therapy, Male, Middle Aged, Treatment Outcome, Outcome Assessment, Health Care, Cross-Over Studies, Stroke, Mobile Applications

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.