Parents of children on the autism spectrum have more asymmetric faces than...
Parents of children on the autism spectrum have more asymmetric faces than other adults of a similar age.
Source: Edith Cowan University

New 3D facial scans to give genetic clues to autism

Researchers from Edith Cowan University (ECU) used sophisticated machine learning techniques to analyse 5000 points on faces to measure facial asymmetry in parents of children on the autism spectrum.

The research team from ECU, UWA and Telethon Kids Institute have previously found children on the autism spectrum were more likely to have greater facial asymmetry than non-autistic children. This is important because better understanding of facial characteristics of autistic people contribute to efforts for early identification and help to understand hereditary (or genetic) causal links. Genetic factors are known to play a major role in autism however there is growing evidence that environmental factors, such as hormones or maternal health, could also influence development of the condition.

In the current study researchers compared the facial asymmetry of 192 parents of autistic children to 163 adults with no known history of autism. They found parents of children on the autism spectrum had more asymmetric faces than other adults of a similar age.

ECU School of Science Research Fellow Dr. Syed Zulqarnian Gilani said the research was an important step in better understanding the genetic causes of autism. "These findings suggest there could be a link between the genes which affect the likelihood of an individual having greater facial asymmetry and autism," he said. "By using these cutting-edge 3D scans of faces combined with machine learning techniques we can distinguish between thousands of subtle differences in faces to determine an overall facial asymmetry score. When we compared those scores, we saw that faces of parents of autistic children were more likely to have higher asymmetry compared to other adults."

New way of looking at autism

According to Dr. Diana Tan, the project's lead author and a Postdoctoral Research Associate at UWA and Telethon Kids Institute, the research helps increase our understanding of autism. "Autism is not traditionally known to be a condition with distinctive facial features, but our research has challenged this notion," she said. "Our study provided evidence that the genetic factors leading to the development of autism may also express in physical characteristics, which leads to our understanding of the interplay between genes, physical and brain development in humans. "We previously examined another facial marker—facial masculinity—that was associated with autism. The next step of this project would be to evaluate the usefulness of combining facial asymmetry and masculinity in determining the likelihood of autism diagnosis."

The research was published in Autism Research.

Subscribe to our newsletter

Related articles

AI may help spot autism early

AI may help spot autism early

A machine learning algorithm can spot abnormalities in pupil dilation that are predictive of autism spectrum disorder in mouse models.

Google Glass helps kids with autism read facial emotions

Google Glass helps kids with autism read facial emotions

Wearing a device that identifies other people’s facial expressions can help children with autism develop better social skills.

Personalized deep learning equips robots for autism therapy

Personalized deep learning equips robots for autism therapy

Machine learning network offers personalized estimates of children’s behavior.

AI reveals brain networks involved in child aggression

AI reveals brain networks involved in child aggression

A machine learning-based approach uncovered disruptions of brain connectivity in children displaying aggression.

Like yin and yang: mindful breathing for pain control

Like yin and yang: mindful breathing for pain control

Researchers compared traditional mindful breathing and virtual reality, 3D-guided mindful breathing to reduce pain.

Using AI for mental health assessment

Using AI for mental health assessment

AI can detect signals that are informative about mental health from questionnaires and brain scans.

An AI that ‘thinks’ like humans

An AI that ‘thinks’ like humans

Creating human-like AI is about more than mimicking human behaviour – technology must also be able to process information, or ‘think’, if it is to be fully relied upon.

Monitoring mental health in cancer survivors with "FAITH"

Monitoring mental health in cancer survivors with "FAITH"

AI-based solution FAITH is designed to monitor the mental health status of people who have undergone cancer treatment.

Using AI and video for early detection of autism

Using AI and video for early detection of autism

Using artificial intelligence, researchers have developed a device for the early detection of autism spectrum disorder in children.

Popular articles

Subscribe to Newsletter