Learning Scan Paths of Eye Movement in Autism Spectrum Disorder
DIGITAL PERSONALIZED HEALTH AND MEDICINE(2020)
Abstract
Eye tracking studies have demonstrated deficits in attention in individuals with Autism Spectrum Disorder (ASD) for a range of different social attention-based tasks. Here we examined social attention skills in a large sample of ASD participants (n = 120), using eye tracking data from a social information processing task, and compared them with a typically developing (TD) group (n = 35). Assuming eye movement parameters are random variables generated by an underlying stochastic process, we modeled the fixation sequences of participants in ASD and TD groups with a Hidden Markov Model. The Regions of Interests (ROIs), modeled as hidden states, corresponded to the true ROIs with a prediction accuracy of >90% for each group. The transition between ROIs revealed bias towards a specific area in the scene in ASD group, which deviated from the TD group. Objective time-dynamic measures of gaze patterns can potentially serve as useful endpoints in ASD diagnosis. Clinical Trial Registration: NCT02299700.
MoreTranslated text
Key words
Autism Spectrum Disorder,eye tracking,Hidden Markov Model
AI Read Science
Must-Reading Tree
Example
Generate MRT to find the research sequence of this paper
Chat Paper
Summary is being generated by the instructions you defined