Description

This is a retrospective multi-centre case-control study to measure sensorimotor anomalies linked to autism spectrum disorder (ASD) to assess the diagnostic accuracy of smartphone-based neurobehavioral evaluations. The primary objective of the study is to evaluate diagnostic accuracy of the smartphone-based assessments compared to a formal clinical diagnosis using machine learning algorithms.

Neurobehavioral testing will be performed using BlinkLab, a smartphone-based platform. The tests include general measurement of spontaneous and stimulus-evoked postural, head, facial, and vocal responses along with specific neurometric tests, including the acoustically evoked eyelid startle reflex (ASR), and tests that involve the modulation of the ASR, including prepulse inhibition (PPI) and habituation (HAB). Children required to participate in two consecutive 15-minute tests. During the experiment, the children will watch an audio-normalized movie while the trials containing the auditory stimuli will be delivered via headphones. For each trial, computer vision algorithms will be used to track and record the position of the participant's facial landmarks over time. The study will compare responses in children with ASD who received a formal DSM-5 based diagnosis prior to study inclusion and neurotypical children that had no formal psychiatric diagnoses.