Dennis P. Wall, PhDAssociate ProfessorDepartments of Pediatrics, Psychiatry (by courtesy) and Biomedical Data ScienceStanford University

Augmented Reality Glasses to Improve Socialization Skills in Children with ASD Interview with:

Dennis P. Wall, PhDAssociate ProfessorDepartments of Pediatrics, Psychiatry (by courtesy) and Biomedical Data ScienceStanford University

Dr. Wall

Dennis P. Wall, PhD
Associate Professor
Departments of Pediatrics, Psychiatry (by courtesy) and Biomedical Data Science
Stanford University What did we already know about the potential for apps and wearables to help kids with autism improve their social skills, and how do the current study findings add to our understanding? What’s new/surprising here and why does it matter for children and families? 

Response: We have clinically tested apps/AI for diagnosis (e.g. in a number of studies.

This RCT is a third phase of a phased approach to establish feasibility and engagement through in-lab and at-home codesign with families with children with autism. This stepwise process is quite important to bring a wearable form of therapy running AI into the homes in a way that is clinically effective.

What’s new here, aside from being a first in the field, is the rigorous statistical approach we take with an intent-to-treat style of analysis. This approach ensures that the effect of the changes are adjusted to ensure that any significance observed is due to the treatment.  Thus, with this, it is surprising and encouraging to see an effect on the VABS socialization sub-scale. This supports the hypothesis that the intervention has a true treatment effect and increases the social acuity of the child.

With it being a home format for intervention that can operate with or without a clinical practitioner, it increases options and can help bridge gaps in access to care, such as when on waiting lists or if the care process is inconsistent. Can you please explain in simple terms how the “Superpower Glass” intervention pairing Google Glass worn by the child with a smartphone app might help kids with autism better recognize faces and emotions and interact with people and read social cues? And to what extent do you think using this would help kids learn these skills themselves, versus provide skills they haven’t developed on their own? 

Response: The glasses provide augmented reality- this is particularly good because it keeps children in their social environment  (as opposed to virtual or mixed reality).  The augmented reality form factor is well suited for helping children engage in social interactions.  The heads up display (a prism) sits in the periphery, and after a short period of time (minutes), is easy to basically ignore except when it provides the social cues.  The glasses act as a message passer.  Passing images to the phone App, which runs the artificial intelligence for real time face tracking and emotion classification.   The Glass’s outward facing camera tracks the world around the child wearing the glasses, sends the image data to the phone which detects faces, emotion and submits them back to the Glass where they are provide to the child through the prism/heads up display in a couple of ways.  First the boundary of the heads up display lights up green.  This green box says the child “You found a face!”, then immediately after the display provides an image – an emoticon or emoji (or if desired a written word of the emotion), which tells the child “You found a happy face!”. In addition, the users can choose to have sound – a voice saying the emotion which comes from the bone conducting speaker in the Glass units themselves.

The green box – you found a face – and emotion cue – you found a happy face – make up 2 of the three components of the intervention.  The third is the App itself which acts as a the game console and main operating system where you launch the games, as well as, importantly (we think), a place to reinforce the learning through parent review.  The activities are logged and the social engagement sessions are recorded so that child and caregiver can go back to an emotion moment and discuss together what worked/didn’t work.

Together these elements of the intervention enable real-life learning. Children learn to seek out social interactions, learn that faces are interesting, and that they can learn what they’re saying/what the faces are telling them.  This is powerful since it encourages social initiations – a form of fostering social motivation – by the child and they’re learning that they can get these things – the emotions of their social partners- themselves.

Reminder that the sessions are relatively short 20 minutes sessions a few times a week and that this learning aid is meant to be short term (relatively speaking).  It gives them the aid they need right when they need it. Boosts confidence etc. Google Glass is a cool idea with a lot of potential and a lot of controversy, especially surrounding privacy concerns for wearers and the people they interact with – so to what extent do you see this idea from a clinical trial being practical or feasible in the real world, and to what extent would it be realistic to expect kids on the spectrum who often have sensory issues and behavior challenges wear something like this all the time? 

Response: I think it is quite practical –

We’ve had over 150 children test the intervention across the studies that we have conducted so far, and have had very few reports of discomfort with the device.  This includes children on the lower function end of the autism spectrum and children with sensory issues, including those who will not wear hats or sunglasses.   There has been near unanimous approval and enjoyment wearing the glass units.  The name superpower was by majority vote among the children who have worn and used it so far.  Several remarked that they are like “super power glasses” or “spy glasses” “magic glasses” etc.  –

The use is in the home and localized there, which has the benefit of working where the social skills and social learning need to originate to boost confidence, especially for the younger ages, and for those with lower baseline levels of social emotional acuity, and it also has the benefit of limiting privacy concerns.  The recordings and the social engagements are with family and friends.    

I am the Founder of has completed licensing of the Glass technology and will be advancing his work forward and working to bring this to market.

General information about Cognoa (provided by Cognoa PR)

Overview on company and licensing agreement:

Stanford is partnering with Cognoa, a behavioral health company that is developing AI-based digital diagnostics and personalized therapies to make earlier diagnoses and effective treatments available to more children to improve outcomes and lower behavioral healthcare costs. Cognoa has received Breakthrough Device designations from the U.S. Food and Drug Administration (FDA) for its lead products, the first digital diagnostic and digital therapeutic devices for autism.

Cognoa is working together with the Stanford team on novel augmented reality digital therapeutic interventions for children with Autism Spectrum Disorder that build upon the advances of the Stanford RCT.  The therapeutic will target the core deficit of social-emotional reciprocity in ASD, with children showing gains in social initiation, facial engagement, emotion recognition, and social responses.  The therapeutic will be delivered via a software system that will be deployed on smartphones combined with a variety of broadly available Augmented Reality platforms.


Voss C, Schwartz J, Daniels J, et al. Effect of Wearable Digital Intervention for Improving Socialization in Children With Autism Spectrum Disorder: A Randomized Clinical Trial. JAMA Pediatr. Published online March 25, 2019. doi:10.1001/jamapediatrics.2019.0285 

[wysija_form id=”3″]


The information on is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.


Last Updated on March 26, 2019 by Marie Benz MD FAAD