Brain cognition gaps reveal associations with dopamine and factors related to brain health through artificial intelligence prediction of functional connectome

In the realm of human neuroscience, researchers are striving to comprehend how individual disparities in brain function correlate with cognitive differences. Despite numerous studies aiming to develop objective biomarkers to forecast intelligence and general cognition, a consensus on domain-specific markers has yet to be reached.

Brain age has been suggested as a potential marker, but recent findings suggest that it offers little extra insight into cognitive decline compared to chronological age, leading to a focus on strategies that directly predict cognition. Employing a deep learning method, a team evaluated the predictive capacity of the functional connectome under different conditions—resting state, movie-watching, and n-back—on episodic memory and working memory performance.

Their results indicate that connectomes during tasks, particularly movie-watching, can predict individual differences across cognitive domains, while resting state connectomes are particularly effective at predicting episodic memory. Moreover, those with a negative brain cognition gap—a situation where brain predictions fall short of actual performance—tended to have lower physical activity levels and higher cardiovascular risk than those with a positive gap.

This insight suggests that understanding the brain cognition gap could provide valuable information regarding factors contributing to cognitive resilience. Additionally, lower PET-derived measures of dopamine binding were associated with a greater brain cognition gap, which was mediated by regional functional variability. Overall, these findings underscore the significance of brain state in connectome-based cognitive prediction and introduce the brain cognition gap as a potentially informative marker of vulnerability to brain function compromise, modulated by dopamine levels.