Feasibility of a Co-Designed Personalized Cognitive Reablement Program Delivered via Digital Voice Assistants for Older Adults Living With Early-Stage Dementia or Mild Cognitive Impairment: Pilot Randomized Controlled Trial.
Tracy Yiannis, Helen Macpherson, David Scott et al.
✦ AI-curated · Sources linked
In 30 seconds
This nonblinded pilot randomized controlled trial assessed the feasibility and potential effectiveness of VOICE-COG, a personalized cognitive reablement program delivered through digital voice assistants, in adults aged 60-85 years with self-reported early-stage dementia or mild cognitive impairment. Thirty participants were randomized to 12 weeks of the program or enhanced usual care. Recruitment was 86%, retention 97%, and mean adherence was 70%; usability was rated marginally acceptable. The intervention group showed a greater increase in memory-strategy use than controls (mean difference 5.0, 95% CI 0.03-10.1, P =.049), with no other significant between-group differences.
Key findings
- Retention was 97% (29/30); intervention adherence ranged from 29% to 100%, with a mean of 70% (SD 17%).
- Mean System Usability Scale score was 56.3 (SD 18.1), indicating marginal acceptability.
- At 12 weeks, 60% (9/15) of intervention participants met or exceeded their personalized goals.
- Memory-strategy scores increased more with VOICE-COG than control: mean difference 5.0 (95% CI 0.03-10.1, P =.049); no other between-group differences were significant.
Why it matters
Home-based reablement may support everyday functioning, but delivery by health professionals can require substantial time, while conventional digital devices may be difficult for some people with cognitive impairment to use. This pilot suggests voice assistants can deliver a personalized program with high retention, while also identifying usability as an issue to address before evaluating effectiveness in a larger trial.
What to keep in mind
This was a small, nonblinded pilot trial with 12 weeks of follow-up. Outcomes beyond feasibility were largely self-reported, and the study was not a full-scale effectiveness trial.