A mobile app that is in the prototype phase has been found to be able to diagnose autism by distinguishing between children with and without autism spectrum disorders (ASD) on the basis of their eye movements. Experts believe that this could be an important tool in diagnosing autism in infants and toddlers.
Further development of the app is being funded by the National Institute of Health in the USA. Its findings were recently published in the Journal of the American Medical Association in a study conducted by the director of the NIH Autism Center of Excellence at Duke University Geraldine Dawson and colleagues.
The analysis of the eye movements to diagnose autism is done by the app based on the eye movements made by the kids while watching videos. As per a press release issued by NIH, “Studies have found that the human brain is hard-wired for social cues, with a person’s gaze automatically focusing on social signals. In ASD, attention to social stimuli is reduced, and researchers have sought to screen for ASD in young children by tracking their eye movements while they view social stimuli.”
The prototype app was tested on 933 toddlers aged between 16 to 38 months. They were shown videos featuring people smiling, conversing, or making eye contact. The gaze patterns of the children during the activity were recorded and analyzed using machine learning tools. Forty of the kids were diagnosed with ASD.
Researchers believe that large-scale studies are needed to confirm the results before using the app in clinical and social settings.