By: Inas Essa

Autism Spectrum Disorder (ASD) is a challenging disorder for doctors to diagnose because it cannot be detected through a physical test like other diseases, but rather on the observation of a person’s development history and behavior.

According to the World Health Organization’s (WHO) recent report, about 1 in 160 children is diagnosed with autism. This is extremely alarming and urges the need for advanced diagnosis and treatment methods. However, several obstacles prevent the ability to quickly and accurately diagnose this disorder as indicated by a systematic review of a number of studies published between 2009 and 2019 on autism, which could be summarized as follows:

• Visual observation of the child and parental interviews are costly and time-consuming.
• The reliability and validity of findings obtained from clinical observations may be subjective, arising from differences in professional training, resources, and cultural contexts.

Hence, the importance of a recent study conducted by researchers at Duke University, USA, and published in the Journal of the American Medical Association (JAMA) Pediatrics. Its results show the success of using a new digital application in detecting one of the main symptoms associated with autism in children.

Eye-gaze Tracking

The app, which combines eye-gaze tracking and machine learning algorithms, could be an accurate and inexpensive new tool to help diagnose early symptoms of autism. This leads to a timely and more fruitful psychosocial intervention that improves the autistic children's ability to communicate effectively.

“We know that babies who have autism pay attention to the environment differently and are not paying as much attention to people… we can track eye-gaze patterns in toddlers to assess risk for autism,” says Geraldine Dawson, Ph.D., director of the Duke Center for Autism and Brain Development, and co-senior author of the study.

Although eye-tracking has been used previously to assess gaze patterns in people with autism, this has required special equipment and expertise to analyze the gaze patterns. She adds, “This is the first time that we’ve been able to provide this type of assessment using only a smartphone or tablet.”

The App in Action

In this study, only an app on smartphones or tablets was used to observe and examine the eye gaze of toddlers with autism spectrum disorder compared to typically developing kids. The displayed clip on the app takes only 10 minutes to administer and uses the front-facing camera to record the child’s behavior. Results of the experiment showed that autistic kids were characterized by reduced attention to social stimuli and a deficit in coordinating gaze with speech sounds.

“It’s amazing how far we’ve come to achieve this ability to assess eye gaze without specialized equipment, using a common device many have in their pocket,” says Zhuoqing Chang, Ph.D., postdoctoral associate in Duke’s Department of Electrical and Computer Engineering and the lead author of the study.

Researchers hope that these new findings have the potential to develop scalable tools to screen autism more effectively and accessibly as it can be used in primary care and is also usable in-home settings. As a result, it could help in getting better results through timely intervention.

References

jamanetwork.com/jamapediatrics

nature.com

corporate.dukehealth.org

who.int/fact-sheets

Media

Autism Screening App

Sample Clip of the Experiment