Scientists use machine-learning approach to predict risk factors of conduct disorder in kids – ET HealthWorld

New Haven: According to a new study, a machine learning approach can evaluate risk factors and predict future developments. Conduct disorder (CD) In ​​children with high accuracy.

The study was published in the journal Biological Psychiatry: Cognitive Neuroscience and Neuroimaging.

Conduct disorder (CD) is a common yet complex Mental disorder Demonstrating aggressive and destructive behavior. Factors contributing to the development of CD include biological, psychological and social domains. Researchers have identified a number of risk factors that can help predict CDs, but they are often considered isolated.

The researchers used baseline data from more than 2,300 children between the ages of 9 and 10 Cognitive development of the adolescent brain (ABCD) study, a longitudinal study of children’s bio-social development.

Researchers “trained” their machine-learning model using previously identified risk factors from multiple biopsychosocial domains. For example, measures include brain imaging (biological), cognitive abilities (psychological), and familial characteristics (social). The model accurately predicted the development of the ladder after two years with more than 90 percent accuracy.

Cameron CarterMD, Biological Psychiatry: Editor-in-Chief of Cognitive Neuroscience and Neuroimaging, said of the study: Than the mother’s mood in response to their children’s emotional behavior. “

The ability to accurately predict who might develop CDs will help researchers and healthcare workers design interventions for at-risk youth with the potential to reduce or even prevent the harmful effects of CDs on children and their families.

“The findings of our study highlight the added value of combining neural, social, and psychological factors to predict behavioral disorders, which is a debilitating psychological problem in young people,” said the senior author. Ariel Baskin-SomersPhD at Yale University.

“These findings promise to develop more precise identification and intervention approaches that take into account the multiple factors contributing to this disorder. They also highlight the usefulness of taking advantage of large, open-access datasets such as ABCD, which collect measures about individuals at each level.” Of analysis, “she concluded.