Using mobile health technology to assess childhood autism in low-resource community settings in India: An innovation to address the detection gap.
Indu Dubey, Rahul Bishain, Jayashree Dasgupta and 11 others
PMID 37458273WHAT IT FOUND
A tablet app assessing social, sensory and motor tasks identified 78% of children correctly across autism, intellectual disability and typical development groups.
It was feasible for non-specialists in homes, but did not separate autism from intellectual disability.
Key findings
01Combining task, questionnaire and interaction metrics yielded 78% overall accuracy in classifying three groups, rising to 86% when distinguishing typical development from any neurodevelopmental disorder.
02Individual measures consistently separated typically developing children from those with autism or intellectual disability, but did not distinguish between the two clinical groups.
03Completion rates exceeded 70% for all tasks in home settings, though missing data was more common in younger children with lower cognitive age.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat 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
All children in the autism group also met criteria for intellectual disability, and many in the intellectual disability group had elevated autistic features, so the study cannot tell whether the app distinguishes autism from intellectual disability in a typical clinic population. The sample was small and drawn from a tertiary clinic and community, limiting generalisability to broader populations. Inter-rater reliability for child social initiation was moderate, so that specific finding should be treated cautiously. Children who did not complete tasks were more likely to be younger and of lower cognitive age, so the results may not apply to the most impaired or youngest children. This is a proof-of-concept study; the app has not been tested prospectively for diagnostic accuracy in a population-based sample.
Declared interests
The authors declared no conflicts of interest. The study was funded by a Medical Research Council Global Challenge Research Fund grant and a Wellcome Trust fellowship.
The easy way to misread this
Do not treat this as a validated diagnostic tool for autism. The study did not test whether the app can distinguish autism from intellectual disability, because every child in the autism group also had an intellectual disability diagnosis. It shows that non-specialists can administer multi-domain tasks in homes, not that the app identifies autism specifically.