Back

The Feasibility of a Smartphone-based Digital Therapeutics for Dysarthria after Stroke (DiDaS): Protocol for a pilot randomized controlled trial

Kim, Y.; Kim, M.; Kim, J.; Song, T.-J.

2022-08-17 rehabilitation medicine and physical therapy
10.1101/2022.08.16.22278857 medRxiv
Show abstract

BackgroundDysarthria is a motor speech disorder occurring from neurological conditions such as stroke. It leads to serious problems in the intelligibility of patients speech, affecting their ability to communicate, quality of life, and emotional well-being. While digital therapeutic approaches for rehabilitation of dysarthria are increasing, clinical evidence of the effectiveness of digital therapeutics has been lacking. A mobile application, D-ST01, has the potential to enhance intensive and repetitive speech rehabilitation due to its high treatment accessibility and its incorporation of gamification, tailored feedback, and interactive functions. MethodsIn our trial, 60 stroke patients with dysarthria within 30 days following the occurrence of stroke will be recruited. In a 1:1 ratio, participants will be randomly assigned to either the intervention group (using D-ST01 for 60 minutes/day, five days/week along with usual stroke care) or the control group (usual stroke care only). This will be a single-blind study in which researchers will evaluate outcome measurements while masked to treatment allocation. After four weeks of treatment intervention, we will compare speech and psychological changes between the two groups. ConclusionsOur study will evaluate the feasibility of the speech treatment application D-ST01 for patients with post-stroke dysarthria. In addition, it will collect evidence for investigating the future efficacy of a large-scale randomized controlled trial. Trial registration numberClinicalTrial.gov #NCT05146765

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.