Conduct disorder (CD), a complex and common psychiatric disorder, is known for its aggressive and destructive behavior. The biological, psychological, as well as social factors that contribute to the development and progression of CD are numerous. Although researchers have identified many risk factors that can help predict CD, they are not often taken into account in isolation. is a new study that uses machine-learning to evaluate risk factors in all three domains and predict the development of CD later.
Elsevier published the study in Biological Psychiatry.
Researchers used baseline data from more than 2,300 children aged 9-10 who were enrolled in the Adolescent Brain Cognitive Development Study (ABCD) Study. This longitudinal study follows the biopsychosocial development and is based on over 2,300 children. Researchers "trained" the machine-learning model by using risk factors that had been identified across multiple biopsychosocial domains. Measures included brain imaging (biological), cognitive capabilities (psychological), family characteristics (social). With over 90% accuracy, the model predicted CD's development two years later.
Cameron Carter, MD is the Editor of Biological Psychiatry. Cognitive Neuroscience. and Neuroimaging. He said about the study: "These striking findings using task-based functional MRI (to investigate the function of reward system) suggest that children of depressed mothers might be more at risk of later depression if their mothers respond to their children's emotions than if the mother's mood .
Researchers and healthcare workers would be able to predict with accuracy who may develop CD. This could help them design interventions for at-risk young people that can minimize or even eliminate the negative effects of CD on their families.
Arielle Baskin Sommers, senior author at Yale University, New Haven CT, USA, said, "“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 senior author Arielle Baskin-Sommers, PhD at Yale University, New Haven, CT, USA. “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.”