A new artificial intelligence algorithm could present an easier way to identify children who may be depressed or anxious.
Although one in five children suffer from depression or anxiety, the conditions can be difficult to diagnose in kids, which is why researchers are excited about a new artificial intelligence algorithm that successfully detected depression and anxiety from children’s speech.
“We need quick, objective tests to catch kids when they are suffering,” lead study author Ellen McGinnis, a clinical psychologist at the Vermont Center for Children, Youth and Families, said in a news release. “The majority of kids under eight are undiagnosed.”
The research, published in the Journal of Biomedical and Health Informatics, used a 90-minute interview to analyze children’s speech patterns. They found that certain patterns, including low-pitched voices, repeatable speech inflections and content, and a higher-pitched response to an unexpected noise, could be used to accurately identify depression and anxiety.
“The algorithm was able to identify children with a diagnosis of an internalizing disorder with 80% accuracy, and in most cases that compared really well to the accuracy of the parent checklist,” said study author Ryan McGinnis.
McGinnis said that the research could present a faster and easier way to identify children who may be depressed or anxious, when compared with the current means of screening for depression in kids.
“This would be more feasible to deploy,” he said.
This is especially important since early intervention can help treat children and avoid future complications, including substance use disorder.
“Thanks to greater neuroplasticity, interventions can be very effective in this population if disorders are identified early in development,” study authors wrote. “However, the current healthcare referral process usually involves parents reporting problem behaviors to their pediatrician and, if functionally impairing, the child is then referred to a child psychologist or psychiatrist for a diagnostic assessment.”
This slow process results in many children being undiagnosed and not accessing the help they need.
“Even if referred, current diagnostic assessments have been shown to capture only the most severely impaired preschoolers, but miss a large number of children who may go on to develop additional clinical impairments,” study authors added.
Using artificial intelligence, coupled with information gathered from a sensor worn for a brief time, could be the future of diagnosing depression and anxiety in children, the study authors said.
“These results point toward the future use of this approach for screening children for internalizing disorders so that interventions can be deployed when they have the highest chance for long-term success,” they wrote.