The Value of a Virtual Assistant to Improve Engagement in Computerized Cognitive Training at Home: Exploratory Study.
Isabella Zsoldos, Eléonore Trân, Hippolyte Fournier and 10 others
PMID 38901017WHAT IT FOUND
Healthy older adults rated a Wizard-of-Oz virtual assistant during cognitive training more favorably than young adults, reporting better comprehension and less fatigue.
This pilot confirms user interest in the interface but proves no cognitive benefit.
Key findings
01Older adults rated the virtual assistant higher on appreciation, comprehension, and engagement, and lower on desire to give up and fatigue, compared to young adults.
02In older adults, higher state anxiety was associated with increased fatigue after the session, while higher intrinsic relevance was associated with decreased fatigue.
03Exercise engagement in older adults correlated positively with their global cognitive functioning scores on the MMSE.
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 participants were healthy adults without cognitive impairment. The study explicitly excluded those with dementia or MCI, so the results do not apply to the target clinical population. The virtual assistant was controlled by a human pilot who could adapt to any situation. An autonomous AI assistant may not provide the same level of support or natural interaction. This was a single session. The study did not test long-term adherence or whether the assistant actually improved cognitive function compared to training without an assistant. Older adults' positive ratings and low fatigue scores may reflect social desirability bias, where they minimized negative experiences to appear well-adjusted.
Declared interests
The cognitive training software was provided by Humans Matter, a company serving health professionals. The study was part of the THERADIA project, funded by Atos (software development) and involving companies like Dynamixyz (motion capture). The authors declare no conflicts of interest.
The easy way to misread this
Do not interpret the high ratings as evidence that this virtual assistant improves cognitive function. The study tested user experience with a human-piloted avatar in healthy adults, not clinical outcomes in patients with cognitive impairment.