Google Glass App Helps Autistic Children with Social Interactions

A prototype software application, to be used with the optical head-mounted display Google Glass, has been designed as a social-skills coach for children with autism spectrum disorder (ASD). A new study published in the open-access journal Frontiers in Robotics and AI finds that the wearable technology can recognize conversational prompts and provide the user with suitable responses in return. Moreover, children find it easy to operate and enjoy using it.

ASD is a life-long condition that affects 1 in 68 people. A defining feature of ASD is difficulties with social communication - which can include initiating and maintaining conversations with others.

"We developed software for a wearable system that helps coach children with autism spectrum disorder in everyday social interactions," says Azadeh Kushki, an Assistant Professor at the Institute of Biomaterials and Biomedical Engineering at the University of Toronto, and Scientist at the Bloorview Research Institute, Toronto, Canada. "In this study, we show that children are able to use this new technology and they enjoy interacting with it."

Children with autism spectrum disorder are often drawn to technological devices and find them highly motivating tools for delivering interventions designed to help them. The problem with existing technology, however, is that using human-to-computer interaction to teach social skills can have the opposite effect to its goal, in that the user becomes socially isolated.

"The interesting thing about our new technology is that we are not trying to replace human-to-human interactions; instead, we use this app to coach children who are communicating with people in real-world situations," explains Professor Kushki. "Children can practice their skills outside of their normal therapy sessions and it can provide them with increased independence in everyday interactions."

Professor Kushki and her colleagues developed the app, named Holli, to be used with wearable technology such as Google Glass -- a head-mounted display in the shape of eyeglasses. It listens to conversations and prompts the user with an appropriate reply.

For example, if the user is greeted by a person who says 'Welcome', Holli will provide various responses to choose from, such as 'Hey', 'Hello' or 'Afternoon'. When Holli recognizes the user's response, the prompts disappear and Holli waits for the next exchange in conversation.

To assess the usability of the prototype software, the researchers asked 15 children with ASD to be guided by Holli when interacting socially. They saw that Holli could complete most conversations without error, and that children could follow the prompts to carry on a social interaction. In fact, Holli was often able to understand what the user was saying before/he she finished saying it, which helped the conversation to flow naturally. As well as demonstrating its feasibility, the children also said how much they liked using it; they enjoyed the prompts and found it easy to use.

"This study shows the potential of technology-based intervention to help children with ASD," says Professor Kushki. "These systems can be used in everyday settings, such as home and school, to reinforce techniques learned in therapeutic settings."

It is hoped that further developments will allow customization for individual users, such as changing prompt location, size and medium, to cater to each child's unique preference and ability. In addition, more work is needed to improve Holli's ability to deal with speech differences that can affect those with autism spectrum disorder.

"Technology has tremendous potential to change the way we think about delivering services to those with ASD. It can augment existing face-to-face interventions to make services accessible in a timely and cost-effective way and help increase treatment effectiveness," concludes Professor Kushki.

Kinsella BG, Chow S, Kushki A.
Evaluating the Usability of a Wearable Social Skills Training Technology for Children with Autism Spectrum Disorder.
Front. Robot. AI 4:31. doi: 10.3389/frobt.2017.00031.

Most Popular Now

Patient Safety must be Central to the De…

An EPR system brings together different patient information in one place, making it easier to access for healthcare professionals. This information can include patients' own notes, test results, observations by...

ChatGPT Shows Promise in Answering Patie…

The groundbreaking ChatGPT chatbot shows potential as a time-saving tool for responding to patient questions sent to the urologist's office, suggests a study in the September issue of Urology Practice®...

Survey: Most Americans Comfortable with …

Artificial intelligence (AI) is all around us - from smart home devices to entertainment and social media algorithms. But is AI okay in healthcare? A new national survey commissioned by...

AI Spots Cancer and Viral Infections at …

Researchers at the Centre for Genomic Regulation (CRG), the University of the Basque Country (UPV/EHU), Donostia International Physics Center (DIPC) and the Fundación Biofisica Bizkaia (FBB, located in Biofisika Institute)...

Video Gaming Improves Mental Well-Being

A pioneering study titled "Causal effect of video gaming on mental well-being in Japan 2020-2022," published in Nature Human Behaviour, has conducted the most comprehensive investigation to date on the...

Machine learning helps identify rheumato…

A machine-learning tool created by Weill Cornell Medicine and Hospital for Special Surgery (HSS) investigators can help distinguish subtypes of rheumatoid arthritis (RA), which may help scientists find ways to...

New Diabetes Research Links Blood Glucos…

As part of its ongoing exploration of vocal biomarkers and the role they can play in enhancing health outcomes, Klick Labs published a new study in Scientific Reports - confirming...

New AI Software could Make Diagnosing De…

Although Alzheimer's is the most common cause of dementia - a catchall term for cognitive deficits that impact daily living, like the loss of memory or language - it's not...

A New AI Tool for Cancer

Scientists at Harvard Medical School have designed a versatile, ChatGPT-like AI model capable of performing an array of diagnostic tasks across multiple forms of cancers. The new AI system, described Sept...

Vision-Based ChatGPT Shows Deficits Inte…

Researchers evaluating the performance of ChatGPT-4 Vision found that the model performed well on text-based radiology exam questions but struggled to answer image-related questions accurately. The study's results were published...

Bayer Launches New Healthy-Aging Ecosyst…

Combining a scientifically formulated dietary supplement, a leading-edge wellness companion app, and a saliva-based a biological age test by Chronomics, Bayer is taking a big step in the emerging healthy-aging...

New AI-Driven Tool could Revolutionize B…

Researchers at the Icahn School of Medicine at Mount Sinai have developed a noninvasive technique that could dramatically improve the way doctors monitor intracranial hypertension, a condition where increased pressure...