Coevolutionary balance of resting-state brain networks in autism

A new study using machine learning to analyze resting-state fMRI brain scans achieved 77.8% accuracy in classifying autism spectrum disorder (ASD). The research introduced 'coevolutionary balance,' a network-level energy measure, revealing significantly altered brain network organization in autistic adults. While accuracy dropped to 64.7% without specific preprocessing, the findings suggest AI can capture systematic differences in functional connectivity. The model showed modest associations with clinical scores but highlights the potential for objective diagnostic tools.