CoChat

Smartphone-Based Speech Therapy for Poststroke Dysarthria: Pilot Randomized Controlled Trial Evaluating Efficacy and Feasibility

Open access
Kim, Yuyoung, Kim, Minjung, Kim, Jinwoo, Song, Tae-Jin · 2024 · Journal of Medical Internet Research

Published version of a preprint

The DOI matches its Crossref record; 79 of the 79 references it cites were found in a registry or an index; 24 of the 60 sources its claims cite were checked for support.

Abstract

Background Dysarthria is a common poststroke speech disorder affecting communication and psychological well-being. Traditional speech therapy is effective but often poses challenges in terms of accessibility and patient adherence. Emerging smartphone-based therapies may offer promising alternatives for the treatment of poststroke dysarthria. Objective This study aimed to assess the efficacy and feasibility of smartphone-based speech therapy for improving speech intelligibility in patients with acute and early subacute poststroke dysarthria. This study also explored the impact of the intervention on psychological well-being, user experience, and overall feasibility in a clinical setting. Methods Participants were divided into 2 groups for this randomized, evaluator-blinded trial. The intervention group used a smartphone-based speech therapy app for 1 hour per day, 5 days per week, for 4 weeks, with guideline-based standard stroke care. The control group received standard guideline-based stroke care and rehabilitation. Speech intelligibility, psychological well-being, quality of life, and user acceptance were assessed using repeated measures ANOVA. Results In this study, 40 patients with poststroke dysarthria were enrolled, 32 of whom completed the trial (16 in each group). The intervention group showed significant improvements in speech intelligibility compared with the control group. This was evidenced by improvements from baseline (F1,30=34.35; P<.001), between-group differences (F1,30=6.18; P=.02), and notable time-by-group interactions (F1,30=6.91; P=.01). Regarding secondary outcomes, the intervention led to improvements in the percentage of correct consonants over time (F1,30=5.57; P=.03). In addition, significant reductions were noted in the severity of dysarthria in the intervention group over time (F1,30=21.18; P<.001), with a pronounced group effect (F1,30=5.52; P=.03) and time-by-group interaction (F1,30=5.29; P=.03). Regarding quality of life, significant improvements were observed as measured by the EQ-5D-3L questionnaire (F1,30=13.25; P<.001) and EQ-VAS (F1,30=7.74; P=.009) over time. The adherence rate to the smartphone-based app was 64%, with over half of the participants completing all the sessions. The usability of the app was rated high (system usability score 80.78). In addition, the intervention group reported increased self-efficacy in using the app compared with the control group (F1,30=10.81; P=.003). Conclusions The smartphone-based speech therapy app significantly improved speech intelligibility, articulation, and quality of life in patients with poststroke dysarthria. These findings indicate that smartphone-based speech therapy can be a useful assistant device in the management of poststroke dysarthria, particularly in the acute and early subacute stroke stages. Trial Registration ClinicalTrials.gov NCT05146765; https://clinicaltrials.gov/ct2/show/NCT05146765

Overview

CoChat Summary

TL;DR

In this pilot randomized evaluator-blinded trial, a smartphone-based speech therapy app plus standard care improved speech intelligibility and dysarthria severity in acute/early subacute poststroke dysarthria compared with standard care alone. The app was feasible with high usability, but adherence was 64% and the trial was small.

Key findings

  • Among 40 enrolled and 32 analyzed (16 per group), speech intelligibility improved in the intervention group from 1.56 (SD 0.89) to 0.69 (SD 1.09) versus control from 2.31 (SD 1.30) to 1.98 (SD 1.43); time F1,30=34.35, P<.001; group F1,30=6.18, P=.02; time-by-group F1,30=6.91, P=.01.
  • Dysarthria severity on NIHSS dysarthria improved: time F1,30=21.18, P<.001; group F1,30=5.52, P=.03; time-by-group F1,30=5.29, P=.03. U-TAP2 percentage of correct consonants showed a significant time effect (F1,30=5.57, P=.03), but group (P=.07) and time-by-group (P=.05) effects were not statistically significant.
  • Quality of life improved over time on EQ-5D-3L (F1,30=13.25, P<.001) and EQ-VAS (F1,30=7.74, P=.009; group F1,30=6.06, P=.02); depression and anxiety showed no significant time or time-by-group effects.
  • Feasibility: 64% (n=20) consistently used the app, >51% (n=16) completed prescribed sessions, mean SUS score was 80.78 (SD 16.27), mCSES showed a group effect (F1,30=10.81, P=.003), and no significant adverse events were observed.

Methods

  • Prospective, randomized, evaluator-blinded pilot trial at 2 stroke centers in South Korea; 40 participants enrolled, 32 completed and analyzed (16 intervention, 16 control). Participants had first-ever acute or early subacute stroke within the past 1 month with dysarthria and MMSE ≥26.
  • Intervention group used a smartphone-based speech therapy app for 1 hour/day, 5 days/week for 4 weeks plus guideline-based standard stroke care; control group received standard guideline-based stroke care and rehabilitation alone.
  • Primary outcome was speech intelligibility from the “Gaeul” passage, rated 0–6 by 3 blinded speech-language pathologists; secondary outcomes included U-TAP2, NIHSS dysarthria, PHQ-9, GAD-7, EQ-5D-3L, EQ-VAS, feasibility, SUS, and mCSES. Repeated measures ANOVA was used under intention-to-treat in SPSS v27, with P<.05.

Limitations

  • Stated: small pilot sample and gender imbalance (25 male, 7 female); only acute/early subacute patients were included; U-TAP2 word-level assessment may not capture rhythm, prosody, or coarticulation in adult poststroke dysarthria; the app was developed only in Korean.
  • Stated: adherence measurement was challenging because of variable internet connectivity and low-specification phones, which may have caused inaccurate log data; adherence was lower than expected.
  • Evident: baseline EQ-VAS differed between groups (intervention 69.88 vs control 52.19; P=.04 in Table 2) despite the text stating no significant baseline differences, which may affect interpretation of quality-of-life group effects.

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

Integrity signals

Registry

Crossref · 10.2196/56417

Cites

79 of 79 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Figure 1 Two components of the smartphone-based speech therapy app. (A) Oro-motor exercise videos for specific muscle stretches with camera mirroring. (B) Speech exercises (sustaining sound) with real-time feedback to improve articulation.
Figure 1 Two components of the smartphone-based speech therapy app. (A) Oro-motor exercise videos for specific muscle stretches with camera mirroring. (B) Speech exercises (sustaining sound) with real-time feedback to improve articulation.CC BY · PubMed Central
Figure 2 Treatment results in the smartphone-based speech therapy app. (A) Session summary with scores based on speech exercise performance. (B) Cumulative analysis presenting daily and weekly or monthly speech outcome scores.
Figure 2 Treatment results in the smartphone-based speech therapy app. (A) Session summary with scores based on speech exercise performance. (B) Cumulative analysis presenting daily and weekly or monthly speech outcome scores.CC BY · PubMed Central
Figure 3 CONSORT (Consolidated Standards of Reporting Trials) flow diagram.
Figure 3 CONSORT (Consolidated Standards of Reporting Trials) flow diagram.CC BY · PubMed Central

Verification

Claims the paper makes

14 Valid · 7 Not valid · 15 Not checked · 84 Own results and interpretations

66 more claims · 2 with their cited sources checked

Create a free account to see all 120 claims and to verify the 2 references still open.

See all claims — free account
  • Probably not a substantial claim. 26
  • It may state two separate claims as one. 31

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

Each contradiction between two passages listed here was confirmed by an independent check.

5 of 5

Citations

Cites

Show all 79 references

Research works printed but not linked: 4

  1. Duffy, JR, 2020, Motor Speech Disorders: Substrates, Differential Diagnosis, and Management. 4th Edition
  2. Isaacson, JE, 2003, Am Fam Physician, 68, 1125
  3. Choi, HS, 2007, J Korean Acad Fam Med, 28, 114
  4. Lu, SC, 2017, Stud Health Technol Inform, 245, 161

Cited by

See all 20

Metadata

Authors
Kim, Y., Kim, M., Kim, J., & Song, T.-J.
Affiliations
  • Yonsei University (KR)
  • Ewha Womans University (KR)
Corresponding author
Song, Tae-Jin
Venue
Journal of Medical Internet Research
Published
2024-04-25
Volume
26
Pages
e56417
ISSN
1438-8871 (ISSN-L)
OpenAlex
W4393052886
Cited by
20
References
76
Citations by year
2026: 9 · 2025: 7 · 2024: 4
FWCI
5.65
Type
journal article
Language
en
Open access
Licence
cc-by
Locations
  • Journal of Medical Internet Research (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • Korea Health Industry Development Institute (RS-2023-00262087)
  • Ministry of SMEs and Startups
  • Ministry of Science and ICT, South Korea (2022-0-00621, RS-2023)
Topics
  • Health Sciences › Health Professions › Speech and Hearing › Voice and Speech Disorders
  • Health Sciences › Medicine › Rehabilitation › Stroke Rehabilitation and Recovery
  • Health Sciences › Health Professions › Occupational Therapy › Assistive Technology in Communication and Mobility
Keywords
mobile health apps, speech intelligibility, dysarthria severity, quality of life, psychological well-being, user acceptance, medication adherence, stroke rehabilitation, consonant accuracy, feasibility, EQ-5D-3L, EQ-VAS, user experience
MeSH terms
Smartphone, Stroke Rehabilitation, Aged, Dysarthria, Feasibility Studies, Female, Humans, Male, Middle Aged, Pilot Projects, Quality of Life, Speech Therapy, Treatment Outcome, 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.