Monday, April 26, 2021

Eye-Tracking App Found to Accurately Identify Toddlers With Autism

A phone/tablet-based app that tracks eye movements and visual attention can accurately distinguish toddlers with autism spectrum disorder (ASD) from typically developing toddlers, according to a study published today in JAMA Pediatrics.

“Current methods for measuring gaze require specialized expensive equipment, calibration, and trained personnel, limiting their use for universal ASD screening, especially in low-resource settings,” wrote Zhuoqing Chang, Ph.D., of Duke University and colleagues. “We demonstrated for the first time, to our knowledge, that an app deployed on relatively low-cost, widely available devices can reliably measure gaze and detect early ASD symptoms related to social attention.”

Chang and colleagues enrolled 993 toddlers aged 16 to 38 months along with their caregivers for this study. During a well-child primary care visit, all caregivers completed a 20-item questionnaire on the presence or absence of various ASD symptoms. Children whose scores on the questionnaire suggested a risk for ASD were referred for a diagnostic evaluation using DSM-5 criteria. The total sample included 40 toddlers diagnosed with ASD, 17 diagnosed with developmental and/or language delay, and 936 classified as typically developing.

During the well-child visit, the children viewed a series of brief videos (each 60 seconds or less) on an iPhone or iPad set on a tripod while sitting on the lap of their caregiver. The videos tested social preference and featured a person talking or doing an activity (blowing bubbles) on one side of the screen and a static toy on the other side. The children were also shown two movies without people or language (floating bubbles and a barking puppy) as a control. While the children were watching the movies, the researchers tracked the direction of their gaze.

Overall, Chang and colleagues noted that these videos “elicited distinctive patterns of gaze in toddlers with ASD, characterized by reduced preference for social stimuli, lower attentional focus on salient social segments of the movie, and previously unknown deficits in the ability to coordinate their gaze with the speech sounds of others.” There were no differences in gaze patterns among toddlers for any of the control movies, the authors noted.

Using the eye-tracking data from all the social preference videos, Chang and colleagues developed an algorithm that could distinguish toddlers with ASD from typically developing toddlers with about 90% accuracy; the predictive ability of any individual video ranged from 76% to 84%.

“We hope a digital screening tool can be complementary to other assessment approaches and ultimately increase the accuracy, exportability, accessibility, and scalability of ASD screening, allowing improved risk detection and earlier intervention,” Chang and colleagues concluded.

To read more on this topic, see the Psychiatric News article “Smart Glasses May Help Children With Autism Recognize Emotions.”

(Image: iStock/shaunl)

Last Day to Apply for New Presidential Task Force on Social Determinants of MH

APA members are invited to apply for appointment to the new Task Force on the Social Determinants of Mental Health, which reflects the theme of incoming APA President Vivian Pender, M.D. There will also be eight work groups that will address major issues related to social determinants of mental health. The appointments begin on May 3 and end at the close of the 2022 Annual Meeting. Those interested should submit a CV, brief summary of expertise, and specific area of interest to by today, Monday, April 26.


Don't miss out! To learn about newly posted articles in Psychiatric News, please sign up here.


The content of Psychiatric News does not necessarily reflect the views of APA or the editors. Unless so stated, neither Psychiatric News nor APA guarantees, warrants, or endorses information or advertising in this newspaper. Clinical opinions are not peer reviewed and thus should be independently verified.