Autism spectrum disorder (ASD) is a complex developmental condition that involves challenges in social interaction, nonverbal communication, speech, and repetitive behaviors.
In the United States alone, about 1 in 54 children is diagnosed with ASD. Boys are four times more likely to be diagnosed with autism than girls. Early diagnosis is crucial for treatment and therapies.
Researchers at Duke University in Durham, North Carolina, USA, used computational methods based on computer vision analysis and a smartphone or tablet to help detect early signs of ASD.
The study, published in JAMA Network, detected distinctive eye-gaze patterns using a mobile device application in a smartphone or tablet. The method can help distinguish toddlers with ASD and typically developing toddlers.
The mobile app, which allows the child to watch short videos, can track gaze, detecting ASD with 90 percent accuracy.
What is Autism spectrum disorder (ASD)?
Autism spectrum disorder (ASD) is a developmental disability that causes effective communication, social, and behavioral problems. Although autism can be diagnosed at any age, the signs and symptoms usually appear in the first two years of a child's life.
People with ASD may communicate, behave, interact, and learn in different ways. Some ASD children may need assistance in their daily lives; others need less. Also, those with this condition's learning and thinking abilities may range from gifted to severely challenged.
The common signs and symptoms include making little or inconsistent eye contact, tending not to look at or listen to people, rarely share the enjoyment of objects or activities by pointing, unable or slow in responding to someone calling their name, facial expressions that do not match what's being said, and problem in understanding another person's actions.
Those with ASD may also have restrictive and repetitive behaviors like repeating specific behaviors or phrases, having focused interest, getting upset in slight changes in a routine, and being sensitive to stimuli, such as light, noise, or temperature.
Toddlers with ASD also tend to prefer looking at objects than people. This is common among children as young as 17 months who are later diagnosed with autism.
The gaze-tracking app
The study highlights the need for technology-based detection tools to spot ASD early. This way, children will be given the appropriate treatment and support more promptly.
The researchers conducted a study in prospective primary care clinics between December 2018 and March 2020. They compared toddlers with and without ASD.
More than 1,500 caregivers of toddlers were invited to participate during a well-child visit. Overall, 993 toddlers completed the study measures, including children between the ages of 16 and 38 months.
First, the children were screened using the Modified Checklist for Autism in Toddlers during routine care.
The team used computer vision analysis to detect toddlers with probable ASD that quantified eye-gaze patterns elicited by the app. The results were compared between toddlers with ASD and those with typical development.
The app was not designed to diagnose autism but to help healthcare practitioners determine a child should be referred to a pediatric specialist for a formal diagnostic evaluation.
The team found that distinctive eye-gaze patterns were spotted in toddlers with ASD, characterized by reduced gaze to social stimuli and social moments during videos or movies. The children each took a test for less than 10 minutes, wherein three videos were shown – an adult playing with a toy or two adults conversing and two control videos showing a puppy or floating bubbles.
The phone or tablet's camera will record the child's gaze as they watch the clips. From there, the researchers referred 79 children to specialists for an autism evaluation. Of these, 40 of the children were later diagnosed with ASD.
The toddlers diagnosed with ASD spent more time looking at the videos with toys than at the person playing with them. Further, the team observed that the children with ASD did not follow the conversation flow as closely as the non-autistic children's gazes.
The app reliably measured both known and new gaze biomarkers that distinguished toddlers with ASD versus typical development," the researchers noted in the study.
"These novel results may have the potential for developing scalable autism screening tools, exportable to natural settings, and enabling data sets amenable to machine learning," they added.
Source:
Journal reference:
Researchers create mini-brains to study autism and test new treatments