Blink rate and facial orientation reveal distinctive patterns of attentional engagement in autistic toddlers: a digital phenotyping approach.

Researchers studied how young children with autism pay attention to videos on iPads. They found that autistic children looked at the screen less often and blinked more (showing less focus) compared to other children. Most importantly, autistic children were less interested in videos with people and social situations, while typically developing children preferred these social videos. This technology could help identify early signs of autism.

This study used computer vision analysis to examine attention patterns in 474 children aged 17-36 months, including 43 with autism diagnoses. Researchers measured facial orientation toward screens and blink rates while children watched social and nonsocial content on iPads. Autistic children demonstrated distinct patterns: they spent less time facing the screen overall, had higher blink rates (suggesting lower engagement), and showed reduced screen orientation during social content compared to nonsocial content. Neurotypical children showed opposite patterns, with increased engagement (lower blink rates, more screen facing) during social versus nonsocial movies.

This digital phenotyping approach offers objective measurement of early social attention differences characteristic of autism.

Digital phenotyping approaches using mobile devices could enhance early autism screening by providing objective measures of social attention. The distinct attention patterns identified may inform early intervention targets, particularly around social engagement skills. Technology-based assessment could improve accessibility and standardization of autism-related evaluations.

Single study design without longitudinal follow-up. Relatively small autism sample (43 children). Study type not specified in metadata, limiting assessment of methodological rigor. No information provided about diagnostic validation or inter-rater reliability of computer vision measurements.

Differences in social attention are well-documented in autistic individuals, representing one of the earliest signs of autism. Spontaneous blink rate has been used to index attentional engagement, with lower blink rates reflecting increased engagement. We evaluated novel methods using computer vision analysis (CVA) for automatically quantifying patterns of attentional engagement in young autistic children, based on facial orientation and blink rate, which were captured via mobile devices. Participants were 474 children (17-36 months old), 43 of whom were diagnosed with autism.

Movies containing social or nonsocial content were presented via an iPad app, and simultaneously, the device's camera recorded the children's behavior while they watched the movies. CVA was used to extract the duration of time the child oriented towards the screen and their blink rate as indices of attentional engagement. Overall, autistic children spent less time facing the screen and had a higher mean blink rate compared to neurotypical children. Neurotypical children faced the screen more often and blinked at a lower rate during the social movies compared to the nonsocial movies.

In contrast, autistic children faced the screen less often during social movies than during nonsocial movies and showed no differential blink rate to social versus nonsocial movies.