Researchers Explore New Technologies to Help People with Autism
Researchers are exploring new ways to use technology to help children and adults with autism. For example, the University of California’s MIND Institute has a targeted program, Autism, Community and Technology, that is working to help make autism services and treatments more accessible and affordable for families in need through technology.
Technology is already widely used to help with communication, organization and other daily activities through mobile apps and other devices. Highlighted below are several examples of new uses of technology being developed to assist people with autism:
Improving social interactions
Researchers at Stanford University are working on a wearable technology, called Superpower Glass, to help children with autism to improve social interactions by helping them to better recognize emotions and to engage with others. Superpower Glass is an artificial-intelligence-driven wearable behavioral intervention. It involves use of a computer vision system running on Google Glass worn by the child and connected to a smartphone app. The system detects facial expressions and emotions of the person in view. It then provides the child with the name of the emotion through both an audio cue and visual cue (emoji).
Researchers compared a group of children receiving standard applied behavioral analysis (ABA) therapy and a group receiving ABA along with the Superpower Glass intervention. The system was used at home where families conducted 20-minute sessions of emotion-identifying games four times a week for six weeks. Children using the glasses showed significant improvements in social interaction compared to the control group.
Another group of researchers, led by Qandeel Tariq, M.A., with Stanford University, is exploring the use of machine learning to help with early identification and diagnosis of autism. They tested the use of home-based videos and machine learning to identify very young children with developmental delays or autism. The researchers developed a tool for rapid detection of autism using short home videos of children taken by parents. The videos were assessed to identify sets of behaviors that align with diagnoses of autism and to determine the children’s risk for autism. The system has an accuracy rate of 92%. Because early identification and treatment are key to better outcomes for children with autism, this type of system may be particularly useful in areas with limited access to autism resources.
Job interview training
Job interviews can be particularly challenging for people with autism because of difficulties with communications skills. Researchers in Japan developed a robot to help with interview training for people with autism spectrum disorder. The young adults learned interview-related communications skills and gained experience and feedback through mock interviews with the robots. The researchers found that the job interview training program using a robot improved job interview skills in individuals with autism.
Voss C., et al. Effect of Wearable Digital Intervention for Improving Socialization in Children with Autism Spectrum Disorder: A Randomized Clinical Trial. JAMA Pediatrics. Published online Mach 25, 2019.
Kumazaki H, et al. Job interview training targeting nonverbal communication using an android robot for individuals with autism spectrum disorder. Autism. Published online Feb. 22, 2019
Tariq Q, et al. Detecting Development Delay and Autism through Machine Learning Models Using Home Videos of Bangladeshi Children: Development and Validation Study. Journal of Medical Internet Research, 2019, 21(4).
Radesky, J. A Wearable Emotion-Recognition Intervention for Children with Autism. NEJM Journal Watch. March 26, 2019.