JMIR Publications

ABSTRACT

Background:

Post-stroke dysarthria, a common speech impairment, affects up to half of all stroke survivors, often reducing their ability to communicate and adversely affecting their quality of life. Although conventional speech therapy for post-stroke dysarthria is effective, access is often limited by time and geographical constraints. Here, digital speech therapy may serve as a scalable alternative. However, few trials have assessed its efficacy, safety, and usability.

Objective:

This study aimed to evaluate whether a smartphone-based speech therapy application is non-inferior to conventional workbook-based therapy in improving speech intelligibility among individuals with post-stroke dysarthria.

Methods:

This single-blind, randomized controlled, non-inferiority trial was performed at three hospitals in South Korea. Adults (≥19 years) with post-stroke dysarthria and without cognitive, sensory, or other speech conditions that could interfere with application use were eligible. Participants were enrolled between July 20, 2023, and April 15, 2024. Participants were randomly assigned (1:1), stratified by stroke phase, using a block randomization method, to receive either a smartphone-based digital therapy application or a conventional workbook-based program for four weeks. The primary outcome was speech intelligibility measured on a 0 to 100 visual analog scale after the intervention. The results were analyzed with analysis of covariance. A non-inferiority margin of 19 points was pre-defined.

Results:

A total of 73 participants were enrolled, of whom 71 completed the intervention and were included in the primary analysis (median age: 62.00 years; interquartile range: 51.00 to 71.00 years). Among them, 37 were assigned to the digital speech therapy group and 34 to the control group. Intelligibility scores improved from 80.16 (SD 19.08) to 92.08 (SD 12.55) in the intervention group, and from 80.67 (SD 16.91) to 88.04 (SD 18.33) in the control group. The adjusted between-group difference was 4.41 (95% confidence interval: 0.02 to 8.80; P=.02), which confirmed non-inferiority. No significant between-group differences were observed in the secondary outcomes related to speech function or psychological status. The digital speech therapy group reported a high system usability score (89.6) and acceptable adherence (64.6%), with no treatment-related adverse events.

Conclusions:

Digital speech therapy was non-inferior to conventional speech therapy workbook in improving speech intelligibility and was feasible across acute-to-subacute and chronic stroke phases. These results support the use of structured, self-guided digital therapy as a scalable and accessible alternative for individuals with limited access to in-person care. Clinical Trial: ClinicalTrials.gov NCT05865106; https://clinicaltrials.gov/study/NCT05865106