Microsoft's Kinect sensor is being used in a university study into making autism in young children easier to diagnose.
As reported by The New Scientist, researchers at the University of Minnesota have set up five Kinect sensors in a classroom, and then tracked the movements of groups of three-to-five year olds.
It's hoped that the peripheral, in conjunction with computer-vision algorithms, will then automatically flag up any children who are hyperactive or unusually still - both of which are common symptoms of autism.
Doctors can then give those kids closer attention and determine whether they are indeed autistic.
Diagnosis of the neural disorder is generally a difficult, time-consuming process, and often involves an experienced doctor observing a child play for extended periods of time in order to pick up on any unusual behaviour.
The university's system is due to be formally showcased at the IEEE International Conference on Robotics and Automation in St Paul, Minnesota later this month.
"The idea is not that we are going to replace the diagnosis, but we are going to bring diagnosis to everybody," explained researcher Guillermo Sapiro.
"The same way a good teacher flags a problem child, the system will do automatic flagging and say, 'Hey, this kid needs to see an expert'."
A UK autism expert urged caution, adding that there are a number of possible symptoms that a system like this would not be able to pick up.
"Early diagnosis is critical in helping people with autism get the support they need," said Caroline Hattersley of The National Autistic Society in London.
"While this technology could potentially identify some signs of autism, there are many factors, such as language delay and limited eye contact that it would miss."