Study finds new program using Google Glass, AI helps children with autism interpret emotions

Published in JAMA Pediatrics, the investigation found that children using the new system showed significant improvements in socialization skills.
By Laura Lovett
03:30 pm

A new artificial intelligence system that employs Google Glass may be a resource for helping children with autism spectrum disorder (ASD) improve socialization skills, according to a recent study published in JAMA Pediatrics

The small clinical trial found that children using the wearable technology at home showed significant improvements in socialization skills, compared to their counterparts that received only the standard of care.

Named Superpower Glass, the new system was designed to “encourage facial engagement” and provide feedback on social situations. The program, which runs on Google Glass, helps kids classify the emotion of the person they are interacting with. Using machine learning, the tools is able to identify eight emotions, and then cue the child via a robotic audio clip and a visual emoticon. 

Families were also given a companion app, which lets the child's caregiver manage the system. 

“The intervention reinforces facial engagement and emotion recognition, suggesting either or both could be a mechanism of action driving the observed improvement,” authors of the study wrote. “This study underscores the potential of digital home therapy to augment the standard of care.”


On average, children who were assigned to use the new system significantly improved their scores on the the Vineland Adaptive Behaviors Scale compared to controls (mean [SD] treatment impact, 4.58 [1.62]; P = .005). Researchers reported positive treatment effects on three other measures, but the improvement was not significant.

One child reported an adverse reaction to the glasses. 


The study included 71 children between the ages of six and 12 with ASD. In order to be eligible for the study, participants had to be attending ABA therapy twice a week in a home setting. Additionally, the children needed to score higher than a 15 on the Social Communication Questionnaire in order to be part of the study. 

Forty children were randomly assigned to the study group and 31 were assigned to the control group.

The tool provides three engagement activity modes including an audio tool prompting emotional identification, guessing a caregiver’s emotion through the use of emoticons and free play. 

Children in the study group were instructed to use each of the three engagement tools at least once. Participants were expected to use the technology for 20 minutes three times a week with their family, and once a week with their ABA behavior interventionist.


According to the CDC, one in 59 children in the US have been identified with ASD. It is about four times more common in boys than girls, according to the agency. 

According to the researchers, applied behavioral analysis is recommended for children with ASD. However, that can be an expensive avenue for many families, costing between $40,000 and $60,000 for one child each year, according to the study. 

Researchers are pitching this technology as a home-based tool for families to use. 


“This is the first randomized clinical trial to demonstrate efficacy of a wearable behavioral intervention for children with ASD, to our knowledge,” the authors wrote. “The intervention teaches children emotion recognition, facial engagement, and the salience of emotion, suggesting the potential for multiple mechanism(s) of action driving the observed improvement in social behavior.”


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!