Skip to content
This site uses cookies. By continuing to browse, you agree to the use of cookies. You can change your settings or learn more here.
Image: Shutterstock/Syda Productions

Short home movies of children can be used to diagnose autism, study finds

“Home videos catches the child in his or her natural environment,” researchers said.
Nov 28th 2018, 6:16 AM 10,412 9

USING SHORT HOME videos of children as a means to diagnose autism can be effective, a new study from the Stanford University School of Medicine has said.

The researchers noted that behavioural therapies for autism – which covers a range of complex developmental disorders – work best when started before the age of five but that diagnosing it can be time-intensive and require a one-on-one assessment with a specialist.

Although the researchers were commenting in the US context, similarly in Ireland those living in some areas face major backlogs to receive an autism spectrum assessment.

Fianna Fáil’s Michael McGrath recently told the Dáil that a waiting time for some of 28 months in Cork was a “sick joke”. 

In this study, senior author Dennis Wall said that home videos offer potential advantages for the diagnosis of autism.

“Using home videos for diagnosis has the potential to streamline the process and make it far more efficient,” he said. 

Home video catches the child in his or her natural environment. The clinical environment can be stark and artificial, and can elicit atypical behaviors from kids.

The researchers asked families for submissions, and received 116 videos of children with autism (average age of 4 years, 10 months) and 46 videos of typically developing children (average age of 2 years, 11 months) that met certain criteria.

This criteria included being 1-5 minutes long, showed the child’s face and hands, showed direct social engagement, and showed opportunities for use of objects such as toys or crayons.

Nine designated “video raters” were asked to evaluate each video using set questions, such as the use of expressive language, making eye contact, expressing emotion etc.

Using mathematical models that recorded the answers to these questions, the researchers were able to determine that three raters were the minimum number needed to generate a reliable score of likelihood that the child had autism.

One of these models, that used five behavioural characteristics, identified autism with 88.9% accuracy overall, correctly labelling 94.5% of children with autism and 77.4% of children without autism.

Wall explained: “We showed that we can identify a small set of behavioral features that have high alignment with the clinical outcome, that nonexperts can rapidly and independently score these features in a virtual environment online in minutes, and that the model we used to combine those features is effective in producing a score that matches the clinical outcome.”

He said that such a system could help streamline a diagnosis and could work well in general paediatric settings. 

The researchers are now repeating their investigation with home videos of young children in Bangladesh to see if the mathematical models translate across cultures. 

Send a tip to the author

Sean Murray


This is YOUR comments community. Stay civil, stay constructive, stay on topic. Please familiarise yourself with our comments policy here before taking part.
write a comment

    Leave a comment

    cancel reply
    Back to top