Kids are not as happy as we usually expect. About 20 percent of them suffer from anxiety and depression, but those internalized disorders are hard to be noticed.
A study published on Wednesday in the journal PLOS ONE described an AI-enabled tool to screen children for internalizing disorders early and accurately.
Researchers from University of Vermont and University of Michigan combined a sensor and an algorithm with the method that elicits the children's behaviors and feelings like anxiety.
The children in a dimly-lit room was told to anticipate something to look in a covered glass box, which turned out to be a fake snake. Then the researchers scored their responses, traditionally through the recorded video, but in the new study, aromatically by a wearable motion sensor and the machine learning algorithm.
The new tool identified differences between children with internalizing disorders and those without. The accuracy reached 81 percent, which was better than the standard parent questionnaire, according to the study.
The algorithm learned that children's movement before the snake was revealed was the most indicative since those with internalizing disorders tended to turn away from the potential threat.
It showed that they anticipated more anxiety, and the turning-away behavior was a negative reaction.
Just 20 seconds of data from the anticipation phase provided by the sensors and algorithm is enough to make a decision while the traditional video coding method may take several months.
It opens up possibilities of large-scale screening to identify those anxious depressed kids.
Early intervention is key because young children's brains are extremely malleable and respond well to treatment, said the paper's co-author Maria Muzik at University of Michigan.
