Structure-decoupled functional connectome-based brain age prediction provides higher association to cognition

Area of Science:

• Neuroscience
• Medical Imaging
• Cognitive Science

Background:

• Brain age prediction is a potential biomarker for brain disease and aging.
• Limited research exists on cognitive associations within the normal aging population.

Purpose of the Study:

• To propose a novel approach for brain age prediction using structure-decoupled functional connectomes.
• To investigate the cognitive associations of brain age prediction differences in a normal aging cohort.

Main Methods:

• Decomposition of functional connectomes into structure-decoupled functional connectomes using structural connectome harmonics.
• Application of the method to a large dataset of normal aging individuals.
• Training brain age prediction models using both original and structure-decoupled functional connectomes.

Main Results:

• Achieved a high correlation between predicted and chronological age (r=0.77).
• Discovered significant relationships between brain age prediction difference and cognitive scores (MMSE, MoCA).
• Structure-decoupled functional connectome-driven brain age prediction difference showed stronger correlations with cognitive scores (MMSE: r=-0.27; MoCA: r=-0.32).

Conclusions:

• The structure-decoupled functional connectivity approach provides a more individual-specific functional network.
• This novel method improves brain age prediction performance.
• The findings offer a better understanding of cognitive decline in aging.