Capturing Expert Knowledge for the Personalization of Cognitive Rehabilitation: Study Combining Computational Modeling and a Participatory Design Strategy.
Ana Lúcia Faria, Maria Salomé Pinho, Sergi Bermúdez I Badia
PMID 30522994WHAT IT FOUND
A free web tool can generate personalized paper-and-pencil cognitive tasks for people after stroke.
It uses expert ratings of task demands, not patient outcomes, so it may help therapists choose tasks but does not show improved recovery.
Key findings
01The researchers created 67 variants of 11 cognitive tasks.
02Twenty external rehabilitation experts rated each variant from 1 to 10 for memory, attention, language, executive functions and difficulty.
03The ratings were used to build a free web tool that can generate a full set of 11 personalized cognitive training tasks from a patient profile.
STILL TO COME
How it was doneWhat they foundWhat it means for OTsWhat 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 study did not test whether the generated tasks improve stroke patients' cognition, daily activities, or communication. Only 11 task types were parameterised, and the authors say this is a small subset of tasks used in practice. The ratings came from 20 rehabilitation experts, which the authors consider a small sample. The experts were from Portugal, so their task preferences may not match other clinical settings. The order in which experts rated the 67 variants and the time they spent were not controlled. The reported ranges cover only the tested parameter combinations.
Declared interests
The authors declared no conflicts of interest.
The easy way to misread this
Do not treat the Task Generator as proven to improve stroke recovery. This paper reports expert ratings and tool development, not patient outcomes, and the authors state that a randomized controlled trial is still ongoing.