Tracking toddlers’ eye movements while they watch videos could help diagnose autism at a younger age – enabling earlier therapies and better results.
Autism spectrum disorder, or autism, is often expressed as difficulty in socially interacting and communicating with others. Some find it difficult to understand what other people are feeling, or find social events upsetting.
Autism is not an illness, nor something to be cured, but a prompt diagnosis allows earlier support for children and adults to help manage the areas of life that are more difficult. The NHS reports approximately 1% of the population is identified as having an autistic spectrum condition, which can include Asperger’s Syndrome.
However, while parents may notice potential signs of autism in children before the age of two years, an official diagnosis is often not made until they turn four or five, losing valuable years to aid development and offer them support.
In a pair of studies led by Dr Warren Jones, researchers discovered that tracking children’s eye movements while watching videos of social interactions could accurately identify those with autism.
One study, published in JAMA Network Open, asked 1,089 participants aged between 16 and 30 months old to watch videos of social interactions between other children at play, roughly one minute long.
Data from an eye-tracking device, which took 120 measurements per second, showed those with an autism diagnosis typically focused on toys of interest, colours and background elements not relevant to the social context, rather than focusing on the interaction between the children in the video.
A second study, published in the journal JAMA, involved 499 children between the ages of 16 and 30 months, all enrolled at specialty centres across the US between April 2018 and May 2019.
Participants were again asked to watch similar videos involving social interactions between other children. On the same day, they underwent a clinical diagnosis to identify whether the participant identified as autistic.
Neither the technician measuring the eye movements nor the clinician giving the diagnosis knew the results of the other test, but when compared, the eye-tracking test was found to correlate with clinical assessments.
Commenting on the research, lead author Dr Jones said: ‘When we make measurements to assess a new child, to use the tool to help diagnose and assess autism, we compare what that child is looking at to what age-matched typically-developing peers look at. If a child with autism is repeatedly missing important social cues in the environment, that’s what we measure.
‘Children with autism are often looking at other background elements, toys, visual features that may be interesting but features that are often not helpful for understanding the social interactions happening in front of them.
‘Social interaction and shared experience are the platform for brain development, so we measure how children are attending to key information in the environment that helps support early development of social, communication, and problem-solving skills.’
In addition to enabling earlier diagnoses, the test could also help eliminate racial and ethnic disparities, an issue reported in at least one particular method of clinical diagnosis.
However, Dr Jones stressed the aim was not to replace clinical diagnosis, but support it.
‘This tool is not intended to replace expert clinicians, but to supplement informed and experienced clinical judgment,’ he said. ‘Autism is a consequential diagnosis, and families of children with autism benefit from clinicians’ support to translate assessment results into plans of care and support as needed.
‘Likewise, the tool is not saying that there’s a right way or a wrong way to look at the world, but rather that we can take direct, objective measures about a child’s behavior to assess a child’s strengths or vulnerabilities and then better support that child’s development.
‘In the US especially, a diagnosis is often the gatekeeper to accessing early intervention and support. We hope that objective measurements can help speed that process.’
Writing in JAMA, the Journal of the American Medical Association, Dr Geraldine Dawson praised the findings.
‘The study by Jones et al represents a significant step forward toward developing more objective tools for early diagnosis of autism,’ said Dr Dawson, director of the Duke Center for Autism and Brain Development.
‘By integrating multiple sources of information – including the eye-tracking test, parent report, and clinical observations – the accuracy, certainty, and efficiency of autism diagnostic assessment could potentially be improved, resulting in fewer missed cases and allowing more children to receive empirically validated early therapies from which they could benefit.’
Dr Dawson also noted that previous studies had demonstrated the ability to monitor gaze in autistic children using only a smartphone or tablet, but stressed further research was required before relying on eye-tracking in practice.
‘Future studies will need to assess how feasible, acceptable, reliable, and efficient the eye-tracking test is when used by clinicians as an aid in autism diagnosis in practice,’ she said.
‘Research will need to assess how information from the eye-tracking test should be weighted and integrated with other sources of information, such as parent report and clinical observation, to arrive at a diagnostic decision.’
MORE : I told my mother-in-law about my son’s autism diagnosis – she ignored us
MORE : My autistic son loves trains, so I work with my laptop on the move
Get your need-to-know
latest news, feel-good stories, analysis and more
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
