A new iPad game can spot autism in children with 93% accuracy.

The breakthrough app is able to identify autism earlier than standard diagnosis methods, which in turn means earlier treatment. The app tracks and records the force and movement of fingers across the screen.

Dr Jonathan Delafied-Butt from the University of Strathclyde says it’s a major breakthrough in the diagnosis of autism in children.

‘This is potentially a major breakthrough for early identification of autism, because no stressful and expensive tests by clinicians are needed.

‘This new ‘serious game’ assessment offers a cheaper, faster, fun way of testing for autism.

‘But more work is needed to confirm this finding, and to test for its limitations.’

The app is able to measure movements and gestures by children using the smart tablet. Greater forces of contact and disruptive movements on the screen will get an autism diagnosis.

It is estimated that 1 in 160 children worldwide have Autism spectrum disorder. The earlier children are diagnosed, the sooner they can start the treatment they need.

A child with autism will usually show evidence of having the disorder from infancy.

The research using the app is a collaboration between the University of Strathclyde and colleagues at the start-up Harimata. They believe the app is a less intrusive way to diagnose the developmental disorder.

The Nature group of Scientific reports states, ‘We decided to test whether or not we could identify autism-specific motor patterns in the gameplay of children as they engaged with a smart tablet computer (iPad mini) under natural conditions and with minimal instructions.

‘We reasoned this would provide more reliable information on the child’s spontaneous motor behaviour than currently available, and allow analysis of the nature of the motor disturbance by accurate measure of the child’s spontaneous, kinematic pattern of purposeful, goal-directed movements in gameplay.’

The data for the research was compiled when the team added two commercially available games on an iPad for the children. The iPads had touch-sensitive screens with embedded movement sensors that capture the children’s fingertip movements as they played the games. The iPad was placed on a desk in front of a child so it would only record the fingers being pushed across the screen. Researchers examined the movement data on 37 children with autism aged three to six years and 45 children without the disorder ranging from ages four through seven.

One game asked the child to cut a piece of fruit and get the child to segregate each piece to four other children. And the second game asked players to colour in an outline of an object, testing the child’s creativity.

Once the children completed the games, the data was put through a machine learning algorithm and the touch sensors were analysed and compared between the two groups of children.
Anna Anzulewicz, director of research at Harimata said, ‘Our aim was to develop a test that would be intuitive, fast, fun and engaging for the children.

‘IPad-based games seemed to be perfect, and they are embedded with powerful sensors, which allow for the precise measurement of the children’s play dynamics.’

The study found ‘Machine learning analysis of the children’s motor patterns identified autism with up to 93% accuracy.

‘Analysis revealed these patterns consisted of greater forces at contact and with a different distribution of forces within a gesture, and gesture kinematics were faster and larger, with more distal use of space.’

‘These data support the notion disruption to movement is a core feature of autism, and demonstrate autism can be computationally assessed by fun, smart device gameplay.’

The accuracy of the results means iPads may be the new way to diagnose autism instead of clinical tests which can be intrusive and expensive.