Back

Enhanced prediction of cognitive function using aging-sensitive networks within the human structural connectome

Madole, J. W.; Ritchie, S. J.; Cox, S. R.; Buchanan, C. R.; Valdes Hernandez, M.; Munoz Maniega, S. R.; Wardlaw, J. M.; Harris, M. A.; Bastin, M. E.; Deary, I. J.; Tucker-Drob, E. M.

2019-12-13 neuroscience
10.1101/2019.12.13.875559 bioRxiv
Show abstract

Using raw structural and diffusion brain MRI data from the UK Biobank (UKB; N = 3,155, ages 45-75 years) and the Lothian Birth Cohort 1936 (LBC1936; N = 534, all age 73 years), we examine aging of regional grey matter volumes (nodes) and white matter structural connectivity (edges) within networks-of-interest in the human brain connectome. In UKB, the magnitude of age-differences in individual node volumes and edge weights corresponds closely with their loadings on their respective principal components of connectome-wide integrity (|rnodes| = 0.459; |redges| = 0.595). In LBC1936, connectome-wide and subnetwork-specific composite indices of node integrity were predictive of processing speed, visuospatial ability, and memory, whereas composite indices of edge integrity were associated specifically with processing speed. Childhood IQ was associated with greater node integrity at age 73. However, node and edge integrity remained associated with age 73 cognitive function after controlling for childhood IQ. Adult connectome integrity is therefore both a marker of early-life cognitive function and a substrate of late-life cognitive aging.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.