April 22, 2022
Machine learning method calculated the risk with 90% accuracy.
A method using machine learning can predict whether children will develop conduct disorder (CD), a complex psychiatric condition that causes destructive and aggressive behavior, according to a new research paper.
The algorithm evaluates psychosocial, social, and biological risk factors. The model’s predictions showed a 90% accuracy rate two years later.
“Findings from our study highlight the added value of combining neural, social, and psychological factors to predict conduct disorder, a burdensome psychiatric problem in youth,” said author Arielle Baskin-Sommers of Yale University.
In the paper, Biological Psychiatry: Cognitive Neuroscience and Neuroimaging, scientists used data from the longitudinal study, Adolescent Brain Cognitive Development (ABCD). More than 2,300 youths, who were aged nine- and 10-years-old, were assessed.
Researchers looked at several different biopsychosocial areas and modified AI algorithms to evaluate all the factors in combination. Cognitive abilities indicated psychological risk factors. Family characteristics contributed to social factors. Brain images demonstrated biological risks.
“These findings offer promise for developing more precise identification and intervention approaches that consider the multiple factors that contribute to this disorder. They also highlight the utility of leveraging large, open-access datasets, such as ABCD, that collect measures about the individual across levels of analysis,” said Baskin-Sommers.
The technology can help children prone to developing conduct disorder with early intervention programs. Healthcare workers and scientists can create strategies to prevent conduct disorder or minimize the effects on the youths at risk and their families.