Artificial Intelligence

AI Finds Brain Networks Associated with Child Aggression

Machine learning provides brain insights for developing psychiatric biomarkers.

Posted October 28, 2021 | Reviewed by Kaja Perina

Source: Geralt/Pixabay

Artificial intelligence (AI) machine learning is rapidly being deployed to help accelerate neuroscience, psychology, and psychiatry research. A new study published in Molecular Psychiatry by researchers affiliated with Yale University shows how AI machine learning can identify patterns of neural connections in the brain associated with aggressive behavior in children.

According to the Yale researchers, this study is a first of its kind. “Disruptions in frontoparietal networks supporting emotion regulation have been long implicated in maladaptive childhood aggression,” wrote the researchers. “However, the association of connectivity between large-scale functional networks with aggressive behavior has not been tested.”

To conduct the study, the researchers used fMRI (functional magnetic resonance imaging) brain imaging data from 129 children while performing a perception task that involves the observing of fearful and calm faces. The task was designed to activate the brain states involved in emotion generation and regulation which are associated with aggressive behavior.

Using AI machine learning, the Yale scientists were able to locate the neural connections that differentiate children with histories of aggressive behavior from those without. AI was able to identify the patterns in the brain networks to predict aggressive behavior.

The Yale scientists then evaluated their findings using a separate dataset and discovered that the same neural networks predicted aggression. According to the study, a predictor of aggression is when there is abnormal connectivity to the dorsolateral prefrontal cortex area of the child’s brain.

This opens the possibility of a potential new type of neural biomarker for aggression in children. Aggressive behavior can be a symptom of children with conduct disorder, intermittent explosive disorder (IED), oppositional defiant disorder (ODD), and attention-deficit/hyperactivity disorder (ADHD). ADHD is one of the most common neurodevelopmental disorders in American children according to the U.S. Centers for Disease Control and Prevention (CDC).

This neuroscience proof-of-concept represents an important initial step towards the possibility of the development of brain biomarkers for child psychiatric disorders in the future by harnessing the predictive and pattern-recognition capabilities of AI machine learning.

“Individual differences in large-scale functional networks contribute to variability in maladaptive aggression in children with psychiatric disorders,” the researchers reported. “Linking these individual differences in the connectome to variation in behavioral phenotypes will advance identification of neural biomarkers of maladaptive childhood aggression to inform targeted treatments.”