The 'breakthrough' iPad game that can spot autism in children with 93% accuracy

• e-mail

The way children play iPad games could reveal if they have autism, researchers have found.

They found those with the condition used greater force and moved their finger in different ways.

It is hoped the app could lead to earlier diagnosis and treatment. 

Scroll down for video 

The children were asked to play games on smart tablet computers with touch-sensitive screens and embedded movement sensors. The main game (pictured) required the children to divide a piece of food and share it among four other children on the screen

'This is potentially a major breakthrough for early identification of autism, because no stressful and expensive tests by clinicians are needed,' said Dr Jonathan Delafield-Butt with the University of Strathclyde. 

'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 researchers  believe the disruption of motor timing and integration may be a unique approach to diagnosing this disorder early so these children can seek the treatment they need. 

Using a smart tablet, children with autism played games that measured their movements and gestures, which revealed they have greater forces at contact and a different distribution of forces within a gesture than those who develop typically.

Autism spectrum disorder is a childhood neurodevelopmental disorder, and its global prevalence is estimated at one in 160 children.

The European and North American prevalence of autism is estimated to be one in 68 children. 

Autism is a development disorder evident from infancy, which affects 1 in 68 children in the US.

In the UK, approximately 700,000 individuals live with autism and the aggregate cost of healthcare and support is more than $30 billion annually.

This novel research is a collaboration between the University of Strathclyde and colleagues at the start-up Harimata, who believes using fun iPad games to track players' hand movements is less intrusive way to diagnose the developmental disorder.

'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,' reads the study published in the Nature group journal Scientific Reports.

'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.'

To begin their work, the team added code to two commercially available games for children in order for them to capture sensor and touch-screen data as they children played.

This novel method is a collaboration between the University of Strathclyde and colleagues at the start-up Harimata, who believes using fun iPad games to track players' hand movements is less intrusive way to diagnose the developmental disorder. To begin their work, the team added code to two commercially available games for children in order for them to capture sensor and touch-screen data as they children played

SWIFTKEY HELPS CHILDREN WITH AUTISM COMMUNICATE

SwiftKey, a keyboard app, has come to their rescue with an experimental application that aims to help these children and their families communicate with each other better.

SwiftKey Symbols is a symbol-based assistive communication app for non-verbal individuals with special needs.

SwiftKey Symbols is free and is part of the company's Greenhouse which handles the experimental projects.

During the study, researchers examined movement data gathered from 37 children with autism, aged three to six years and 45 children without the disorder ranging from ages four through seven. Pictured is SwiftKey's keyboard app that helps kids with autism communicate with others

A majority of the available communication tools are too slow at selecting the particular image a child might choose to express what they want to say.

The app is just like texting, but instead of using letters to form sentences users choose images, which are hand drawn by a member of SwiftKey's team.

There are dozens of images all listed in an appropriate category such as people, colors, toys and they can also use the smart suggestion bar to help them build their thought.

This option uses predictive language technology that can accurately guess the next word, expression or even suggest a word based on the images that have already been chosen. 

'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,' said Anna Anzulewicz, director of research at Harimata.

During the study, researchers examined movement data gathered from 37 children with autism, aged three to six years and 45 children without the disorder ranging from ages four through seven.

Using a smart tablet, children with autism played games that measured their movements and gestures, and researchers found these patterns consisted of greater force of impact that those who develop typically

The children were asked to play games on smart tablet computers with touch-sensitive screens and embedded movement sensors.

An iPad mini was placed on a table in front of the child, so the only movement gathered would be their fingers pushing across the screen.

The main game required the children to divide a piece of food and share it among four other children on the screen.

And the second game focused on creativity that asked players to colour in an outline of an object.

Once the games were completed by all of the children, the researches ran the data through a machine learning algorithm using the 262 features from the touch screen and sensors – and then they compared each of the two groups' results.

'Machine learning analysis of the children's motor patterns identified autism with up to 93% accuracy,' reads the study.

The second game (pictured) focused on creativity that asked players to colour in an outline of an object. Once the games were completed by all of the children, the researches ran the data through a machine learning algorithm and then compared each of the two groups' results

'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.'