Brief Report: Evaluation of an Intelligent Learning Environment for Young Children with Autism Spectrum Disorder.
Zhi Zheng, Zachary Warren, Amy Weitlauf and 4 others
PMID 27561902WHAT IT FOUND
A gaze-based prompt system was tolerated by all 16 young children in a pilot.
Toddlers with ASD turned toward their name on every trial, usually after one name call. It shows feasibility, not proven therapy.
Key findings
01All 16 children tolerated the system, and no session was stopped because of distress or engagement problems.
02Toddlers with ASD, all of whom had ADOS-2 response-to-name challenges, eventually turned toward the target on every trial; most hits were at Level 1, with average prompt level 1.23 and average time 3.07 seconds.
03The gaze detection was validated in 100 trials with a 5% error rate for large monitor regions.
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
Only 16 children were studied, and each child had one short session, so the study cannot show how the system works over time. The ASD and TD groups were analysed separately and were not controls, so similarities between them cannot be read as a treatment effect. The study measured feasibility and tolerability, not whether the system improved social communication or learning. The gaze-detection error rate was tested only for large monitor regions; smaller interactive objects may be harder to detect. The TD comparison group did not have the same rigorous autism-assessment data as the ASD group. Response times varied widely among children.
The easy way to misread this
Do not read this as proof that the system improves response to name or social communication. It was a 16-child pilot feasibility study, the groups were not compared as controls, and the paper reports only tolerability and in-session responses.