Digital tools for direct assessment of autism risk during early childhood: A systematic review
Tablet games and video AI can spot autism risk in toddlers with good accuracy, but they are still pilot tools.
01Research in Context
What this study did
The team hunted for studies that use phones, tablets, or smart cameras to spot autism risk in toddlers.
They kept 18 papers. Every study let kids play short games or filmed them while they moved.
No doctor had to watch live; the software scored eye gaze, smiles, and walking patterns.
What they found
Most apps correctly picked the autistic toddlers about 8 times out of 10.
The tools are still lab toys; only a few have moved to clinics or homes.
Still, the review shows machines can flag risk without a specialist in the room.
How this fits with other research
van den Broek et al. (2006) showed paper checklists like M-CHAT miss many higher-functioning kids. The new digital games track movement and gaze, so they may catch kids who pass paper screens.
Bong et al. (2021) proved a 10-minute caregiver interview plus play observation already works well. Digital tools aim to replace that human time, but they have not beaten those accuracy numbers yet.
Préfontaine et al. (2024) took the next step: after a child is diagnosed, machine learning predicts how much ABA will help. Kremkow et al. (2022) focuses on the first step—finding risk—while Isabelle focuses on the last step—forecasting progress.
Why it matters
You can start using tablets today to collect extra data during intake. Let the toddler tap bubbles or watch faces while you interview parents. The app gives a second opinion that does not tire like human eyes. Until the tools are FDA-cleared, treat them as screening aides, not diagnoses.
Want CEUs on This Topic?
The ABA Clubhouse has 60+ free CEUs — live every Wednesday. Ethics, supervision & clinical topics.
Join Free →Film a 2-minute play sample on your tablet and run free autism-risk demo software; compare its flags with your M-CHAT results.
02At a glance
03Original abstract
<h4>Lay abstract</h4>The challenge of finding autistic children, and finding them early enough to make a difference for them and their families, becomes all the greater in parts of the world where human and material resources are in short supply. Poverty of resources delays interventions, translating into a poverty of outcomes. Digital tools carry potential to lessen this delay because they can be administered by non-specialists in children's homes, schools or other everyday environments, they can measure a wide range of autistic behaviours objectively and they can automate analysis without requiring an expert in computers or statistics. This literature review aimed to identify and describe digital tools for screening children who may be at risk for autism. These tools are predominantly at the 'proof-of-concept' stage. Both portable (laptops, mobile phones, smart toys) and fixed (desktop computers, virtual-reality platforms) technologies are used to present computerised games, or to record children's behaviours or speech. Computerised analysis of children's interactions with these technologies differentiates children with and without autism, with promising results. Tasks assessing social responses and hand and body movements are the most reliable in distinguishing autistic from typically developing children. Such digital tools hold immense potential for early identification of autism spectrum disorder risk at a large scale. Next steps should be to further validate these tools and to evaluate their applicability in a variety of settings. Crucially, stakeholders from underserved communities globally must be involved in this research, lest it fail to capture the issues that these stakeholders are facing.
, 2022 · doi:10.1177/13623613221133176