AI detects anxiety, depression in children's speech patterns

Machine learning analysis can identify internalizing disorders such as anxiety and depression in audio recordings of children, according to a new study published in the Journal of Biomedical and Health Informatics.

In the study, researchers from the University of Vermont Medical Center in Burlington assigned 71 children aged 3 to 8 to complete the Trier-Social Stress Task. Each child improvised a three-minute story while an adult judge offered only neutral or negative feedback, with the intention of causing feelings of stress and anxiety in the subject.

Recordings of the children's stories were then analyzed by a machine learning algorithm. The algorithm was trained to recognize eight speech pattern features indicative of an internalizing disorder, including low-pitched voices, repeatable speech inflections and content, and a higher-pitched response to surprising stimuli.

When compared with a diagnosis from a traditional clinical interview and parent questionnaire, the artificial intelligence was able to diagnose internalizing disorders in the children with 80 percent accuracy. According to the researchers, the algorithm is thus more accurate than a diagnosis based on parent-reported symptoms and also many times faster, since clinical evaluations can take over an hour and the algorithm processed the recording within seconds.

More articles about AI:
IBM Watson imaging AI goes live in 1st health system
Recursion Pharmaceuticals releases open-source 300-gigabyte dataset to improve AI use in biotech
How AI helped 2 health systems automate case reviews & reduce claim denials

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Webinars

Featured Whitepapers