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

Abstract

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.

Early detection of autism using digital behavioral phenotyping

“…During the social and nonsocial movies, CVA was used to extract the blink rates as indices of attentional engagement, referred to as blink rate 24 .…”

Information Dynamics of the Heart and Respiration Rates: a Novel Venue for Digital Phenotyping in Humans

“…This resulted in time series with length 60 × 24 × D = 1440 × D, per participant, per HR and RR. Here, 60 is the number of data points per hour and D ∈ [1,2,3,4,5,6] denotes the number of days of experiment that were available from every individual. For instance, two individuals with whose number of days D = 1 and D = 3 would have HR and RR time series of length 1440 × 1 = 1440 and 1440 × 3 = 4320, respectively.…”

“…Humans' phenotype refers to observable characteristics and traits [1]. They range from individuals' developmental processes [2,3] to their behavior [4] and (electro)physiology [5,6]. Recent decades have witnessed a substantial growth in human phenotyping [1].…”

“…The state of a (forced) harmonic oscillator is indeed three dimensional[93, p. 7] 4. This relation is through the Fisher Information.…”