A new brain-age modeling framework links predictions of a person’s age from brain scans to specific functional connectivity circuits, revealing stage-dependent reorganization across large-scale networks during mid- to late adulthood. The study, published in Brain Informatics, was led by Yikang Cao, Marco Castellaro, Marco Zorzi and Alessandra Bertoldo.
Brain-age models estimate how old a brain appears from its functional connectivity patterns, which are typically derived from resting-state functional MRI. These models have shown promise for characterizing large-scale age-related network changes and advancing understanding of neural aging mechanisms. However, existing approaches have faced a persistent challenge: achieving both robust predictive performance and stable identification of the connectivity signatures that drive predictions.
To address this, the researchers developed a framework that integrates a novel neural architecture with an interpretability module. Resting-state fMRI data from 599 adults aged 36 to 95 years were used to compute whole-brain functional connectivity. The team built an Orthogonal Auxiliary Guidance Convolutional Autoencoder, or OAG-CAE, which learns age-relevant latent representations while separating out age-residual variation, followed by a regressor for brain-age prediction.
The key methodological innovation is a SHAP-guided PCA back-projection module. It applies SHAP, a technique for attributing a model’s output to its inputs, to PCA-reduced functional connectivity features, propagates the attribution through the latent representation and predictive pathway, and then projects the PCA-level attributions back into connectivity space. This allows the model’s age predictions to be localized to specific brain circuits rather than remaining opaque.
The resulting brain-age model achieved robust accuracy across mid- to late adulthood, with a mean absolute error of 6.308 plus or minus 0.566 years and an R-squared of 0.702 plus or minus 0.043. These figures indicate that the model captured a substantial share of age-related variance in functional connectivity while maintaining stable performance across the adult lifespan studied.
SHAP analysis revealed systematic patterns of functional reorganization with aging.
A striking finding was that a substantial proportion of these negatively identified connections followed an inverted U-shaped trajectory, peaking around age 70. This non-linear pattern appeared in within-network effects in the somatomotor and default mode networks, and in cross-network thalamo-cortical and somatomotor-ventral attention links. The result suggests that these circuits do not decline linearly but instead undergo a transition during mid- to late adulthood.
In contrast, positive SHAP-identified connectivity emerged mainly in cerebellar links with the default mode, frontoparietal and dorsal attention networks, as well as in default mode-visual and dorsal attention-thalamic pathways. The opposing directions of these attribution patterns point to a redistribution of functional coupling across the aging brain rather than a uniform change.
By integrating OAG-CAE-based latent representation learning with SHAP-guided PCA back-projection, the study establishes an interpretable brain-age modeling framework that links prediction to specific connectivity circuits. The identified signatures reveal stage-dependent reorganization across large-scale networks, including non-linear transitions during mid- to late adulthood.
The authors note that these findings offer new insight into large-scale functional brain aging and provide a structured basis for future investigations in pathological aging and independent cohorts. The framework is presented as a methodological foundation for follow-up studies rather than a clinical tool, and the reported signatures will require validation in further research before any broader application.
Subject of Research: Interpretable brain-age modeling of functional connectivity changes in adult brain aging
Article Title: Interpretable brain-age modeling reveals network-level reorganization in functional brain aging
Article References: Cao, Y., Castellaro, M., Zorzi, M., & Bertoldo, A. (2026). Interpretable brain-age modeling reveals network-level reorganization in functional brain aging. Brain Informatics. https://doi.org/10.1186/s40708-026-00331-z
Image Credits: AI Generated
DOI: 10.1186/s40708-026-00331-z
Keywords: brain-age prediction, functional connectivity, resting-state fMRI, SHAP interpretability, autoencoder, default mode network, somatomotor network, thalamo-cortical pathways, cerebellum, aging, machine learning, neuroimaging
News Source: Cassandra Pierce. (October 29, 2026). AI model reads brain connectivity to trace how networks reorganize with age. Scienmag.
