Eye on Autism: New eye-tracking tool may detect symptoms at just 16 months
Children can now be diagnosed with autism when they are as young as two years old, thanks to a revolutionary device designed by Warren Jones and Ami Klin
A new eye-tracking tool to understand how children 'look' at their surrounding social environment could help with diagnosing autism as early as 16 to 30 months of age, scientists say.
Visual engagement of nearly 500 children in this age group was measured by monitoring their eye movements as they watched video scenes of social interaction, the researchers from Marcus Autism Center, Children's Healthcare of Atlanta, US, said in their study.
Data regarding what social information children looked at and what they did not was thus collected.
Using this data, a diagnostic prediction of autism was provided and compared with expert clinical diagnosis of autism, which is the current gold standard.
The tool measuring social visual engagement gave 71 per cent true positives and 80.7 per cent true negatives compared to the expert diagnoses, the study published in the Journal of the American Medical Association (JAMA) and on JAMA Network Open said.
A 'true positive' here is when the child in question is clinically diagnosed with autism and the newly developed diagnosis tool re-affirms it, whereas a 'true negative' is when the child is clinically diagnosed to not have autism and this new tool re-affirms that.
This implies the tool still isn't as good as expert human professional diagnosis, since there were false positives 29 per cent of the time, where experts did not think the child was actually autistic, and false negatives 20 per cent of the time, where the visual engagement tool did not see any unusual pattern but an expert diagnosed the child as autistic based on other information.
However, the results are promising enough that the tool could help pave the way for an earlier and confident diagnosis in many children, in addition to reducing burdens on the healthcare system by cutting down wait times for assessments, the researchers said.
"The far-reaching implications of these results may mean that children who currently have limited access to expert care and face two or more years of waiting and referrals before finally being diagnosed at age four or five may now be eligible for diagnosis between the ages of 16 and 30 months," said Ami Klin, the study's co-author.
Children diagnosed with autism spectrum disorder (ASD), a developmental disability caused by differences in the brain, often experience problems with social communication and interaction, and many show restricted or repetitive behaviours or interests, according to the Center for Disease Control and Prevention (CDC), US.
Autistic children may also have different ways of learning, moving or paying attention.
Previous studies have showed that differences in visual engagement of autistic children with their social surroundings emerge early in infancy and are directly related to individual genetic differences.
Warren Jones, lead author, and Ami Klin have developed this technology to reliably measure these differences as a biomarker for clinicians to use, they said.
"The results show that the way in which young children look at social information can serve as an effective and objective biomarker for early signs of autism," said Jones.