NEW DELHI: In a development that could help millions of children with autism and related neuro-developmental disorders in India and other low-income countries, a new app that tells autism behaviour has been successfully tested.
At present, a diagnosis of autism typically depends on clinical assessments by highly-trained professionals, using rich resources. It is a challenge in low-income settings. The new app called START (Screening Tools for Autism Risk using Technology) was tested at homes by non-specialist healthcare workers, educated to the high school level, using researchers from India, the UK and the US. The app was tested with 131 two- to eleven-year-olds living in poor neighbourhoods of Delhi.
The research was funded by a grant from UKRI Medical Research Council Global Challenges Research Fund. Children with autistic conditions preferred looking at geometric patterns rather than social scenes. They are fascinated by predictable, repetitive sensory stimuli and have more trouble completing precise tasks with their hands.
The app includes tasks, a questionnaire, and observational assessments of aspects of behaviour that index social, sensory and motor function. Individual metrics from each task show a consistent pattern of differences between typically and atypically developing children. Combining the information from multiple measures within the app resulted in high classification accuracy for the three groups of children – autism spectrum conditions; intellectual disability and typically developing.
The app was 86 per cent accurate in identifying children with any neurodevelopmental disorders, and 78 per cent accurate in specifically identifying autism. This performance is significantly higher than standard screening assessments for neurodevelopmental disorders used by non-specialists. The results could help faster identification of children with autism.