Bibliographic record
Abstract
Back to table of contents Previous article Next article Tech TimesClinical and Research NewsFull AccessSmart Glasses May Improve More Than Eyesight in Children With ASDNick ZagorskiNick ZagorskiSearch for more papers by this authorPublished Online:13 Dec 2016https://doi.org/10.1176/appi.pn.2016.12b12AbstractAn engineering student in Toronto wants to use Google Glass technology to encourage more functional independence in autistic children.iStock/Dean MitchellChildren with autism spectrum disorder (ASD) tend to be drawn to technology—an affinity that some believe could be tapped to improve their social and behavioral skills.To date, however, most tech-based therapies for ASD, including mobile applications, video games, and even interactive robots (Psychiatric News, October 2, 2015) offer only an indirect means for improving social behaviors.Ben Kinsella, a graduate engineering student at Toronto’s Holland Bloorview Kids Rehabilitation Hospital, thinks that Google Glass—an Internet-connected eyewear device in which text appears on the interior of the lens—might offer a new way to coach patients with ASD through more direct social interactions.After hearing from parents of children with ASD that they were looking for new ways to encourage their children to engage with others, Kinsella developed a tablet-based game that simulated common real-world scenarios. In the game, the player is encouraged to interact with a digital avatar to place an order at a fast-food restaurant. After being asked “What would you like to order?” the tablet offers a series of prompts such as “I would like a hamburger, please” or “Do you have any specials today?” The player repeats one of these prompts aloud to continue the conversation. With each successful encounter with the avatar, the game adds elements to mimic a real-world conversation more closely; for example, at higher levels of the game, the game no longer offers prompts and background noise increases.Like other machine-learning programs, this application remembers the more popular choices the player makes over time and gradually offers more personalized options during conversations. Kinsella later adapted his application so that instead of relying on a digital avatar, the program would record and analyze questions directly from a human. “Many studies have shown that children with autism prefer touchscreens, so sticking with a tablet as the platform seemed a natural choice,” Kinsella said. But, he soon realized that programming the language software into Google Glass might encourage the children to look at their partner during a conversation—an important component of normal communication.Kinsella and his colleagues at Bloorview’s Autism Research Center recently conducted a focus group of software-enabled glasses with a group of older children (average age of 12) with ASD. As part of this focus group, the researchers evaluated the accuracy of the recording software, response time for each answer, and the comfortableness of the glasses.The results of the pilot were positive in terms of program accuracy and user satisfaction, Kinsella said, but more work needs to be done to refine the “intelligence” of the software.“What works with the glasses is that the children focus on the visual overlay and not the other person, so it does make the interaction more comfortable for the child,” he said.Kinsella has presented his device at several technology and science conferences, and among the comments he has heard from medical professionals is a concern that this listen-and-prompt technology may reinforce the behavioral rigidity often displayed in ASD children.Shawn Sidhu, M.D., is an assistant professor of psychiatry at the University of New Mexico who chaired a session featuring Kinsella at the American Academy of Child and Adolescent Psychiatry annual meeting in October. Sidhu emphasized that it is important for parents to view these glasses as a training opportunity, not as an assistive device like a hearing aid.“Using the glasses sparingly to encourage independence … should keep children from becoming reliant on them in order to have a conversation.” As an added measure, Kinsella is developing more intelligent prompting mechanisms, such as leaving key words blank so the wearer must think of what they want (“I would like a ____, please”) or occasionally incorporating a brief delay before prompts appear to encourage the wearer to speak freely. “What’s most important is that we get this right in terms of having a product that is supported by clinical evidence that can help kids and families with ASD,” he said. “There is a lot of tech for autism out there already, but we need to ensure that available technology is evidence based. This is a novel idea, but we don’t want to push it out for the sake of pushing it out. We want to make a difference.” ■ ISSUES NewArchived
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".