Exploring the Effectiveness of Technology-Based Interventions in Aphasia Rehabilitation: A Systematic Review.
Bader Alhejji, Stuart Cunningham, Samantha Dorney and 1 others
PMID 42706959WHAT IT FOUND
Technology-based word-finding therapy helped trained words when therapy reached the recommended 20 hours.
Other language domains were less consistent, and AI assessment accuracy did not yet show real-life patient benefit.
Key findings
01Technology-based word-finding therapy produced meaningful improvements in trained-word retrieval when studies reached the recommended 20-hour dose, and this was the strongest evidence domain in the review.
02Where technology groups did better than control groups, the review says it is hard to tell whether the gain came from the technology itself or from more practice time.
03AI and automated speech recognition models sometimes reached very high accuracy on test datasets, but this has not yet shown patient-level benefit in real clinical care.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The review could not pool results statistically because study designs, outcome measures, technology types, doses and follow-up periods varied too much. 49 studies had fewer than 50 participants. 50.7% of included studies were rated low quality, and many had limited blinding or unclear analysis. Dose was often below the recommended 20 hours, especially for reading, where 33.3% of studies with reported dose met the threshold. Screening and data extraction were mainly done by one reviewer. No grey literature or citation searching was done, so relevant studies may have been missed. Most studies were in English and in hospital or university settings in high-income countries. Because many interventions combined technology with therapist support, extra practice, accessibility features or remote supervision, the review could not separate the effect of the technology itself.
Declared interests
Author Rebecca Palmer contributed to two studies reported across three papers in this review, and the paper states this did not influence selection, appraisal or interpretation. No other competing interests were declared. The work was funded by King Abdulaziz University.
The easy way to misread this
Do not conclude that any digital aphasia tool will improve communication. The strongest evidence is for trained word finding at the recommended 20-hour dose, and other domains were mixed or limited by small studies, low dose, or extra practice time rather than proof of the technology itself.