Back

Fingerprinting of brain disease: Connectome identifiability in cognitive decline and Alzheimer s disease

Stampacchia, S.; Asadi, S.; Tomczyk, S.; Ribaldi, F.; Scheffler, M.; Lovblad, K.-O.; Pievani, M.; Fall, A.; Preti, M. G.; Unschuld, P.; Van De Ville, D.; Blanke, O.; Garibotto, V.; Amico, E.; Blanke, O.

2023-10-23 neuroscience
10.1101/2022.02.04.479112 bioRxiv
Show abstract

In analogy to the friction ridges of a human finger, the functional connectivity patterns of the human brain can be used to identify a given individual from a population. In other words, functional connectivity patterns constitute a marker of human identity, or a brain fingerprint. Yet remarkably, very little is known about whether brain fingerprints are preserved in brain ageing and in the presence of cognitive decline due to Alzheimers disease (AD). Using fMRI data from two independent datasets of healthy and pathologically ageing subjects, here we show that individual functional connectivity profiles remain unique and highly heterogeneous across early and late stages of cognitive decline due to AD. Yet, the patterns of functional connectivity making subjects identifiable, change across health and disease, revealing a functional reconfiguration of the brain fingerprint. We observed a fingerprint change towards between-functional system connections when transitioning from healthy to dementia, and to lower-order cognitive functions in the earliest stages of the disease. These findings show that functional connectivity carries important individualised information to evaluate regional and network dysfunction in cognitive impairment and highlight the importance of switching the focus from group differences to individual variability when studying functional alterations in AD. The present data establish the foundation for clinical fingerprinting of brain diseases by showing that functional connectivity profiles maintain their uniqueness, yet go through functional reconfiguration, during cognitive decline. These results pave the way for a more personalised understanding of functional alterations during cognitive decline, moving towards brain fingerprinting in personalised medicine and treatment optimization during cognitive decline.

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.