2020/05/26 by Karan Ahuja, Ahuja, Karan, Abhishek Bose +15
Neuroscience · Social Sciences · Health Professions · #Autism Spectrum Disorder Research #Child Development and Digital Technology #Assistive Technology in Communication and Mobility
paper · pdf · doi:10.48550/arxiv.2005.12951
Autism often remains undiagnosed in adolescents and adults. Prior research\nhas indicated that an autistic individual often shows atypical fixation and\ngaze patterns. In this short paper, we demonstrate that by monitoring a user's\ngaze as they watch commonplace (i.e., not specialized, structured or coded)\nvideo, we can identify individuals with autism spectrum disorder. We recruited\n35 autistic and 25 non-autistic individuals, and captured their gaze using an\noff-the-shelf eye tracker connected to a laptop. Within 15 seconds, our\napproach was 92.5% accurate at identifying individuals with an autism\ndiagnosis. We envision such automatic detection being applied during e.g., the\nconsumption of web media, which could allow for passive screening and\nadaptation of user interfaces.\n