Relating Global and Local Connectome Changes to Dementia and Targeted Gene Expression in Alzheimer's Disease

Critical Regions and Connections Form Pathways and Clusters in the Mouse Brain

Connectome network analysis across multiple species should help identify principles of brain function. Here, we examined three fundamental properties-global efficiency, global betweenness centrality, and global clustering-in the mesoscale tract-tracing data of the mouse connectome; and conducted vulnerability analysis to identify the critical regions and connections based on the loss in network function when each brain region (213) and connection (16,594) was removed. Robustness tests examining noise effects were also conducted. There were five key findings. First, we identified eight critical regions and 38 critical connections, with more central, limbic regions dominant; and with robustness analysis showing (a) the importance of connection strength; and (b) the findings being robust to noise. Second, although critical regions and connections were significantly based on their local network properties, global influences sometimes deviated from local ones (e.g., critical globally but with lower local scores), thereby revealing global-level interactions. Third, the critical components organized into two main pathways (one from piriform cortex to globus pallidus; the other, entorhinal cortex to the amygdala), and two main clusters (centred on caudoputamen and entorhinal cortex). Fourth, for brain function, all main categories from perception to action were represented: e.g., olfaction (piriform cortex), learning and memory (entorhinal cortex), affect (amygdala and caudoputamen), and cognitive and motor processing (caudoputamen, globus pallidus). Finally, the claustrum was intriguingly identified as critical, perhaps for information integration and motor translation. Vulnerability analysis provides a unique approach to characterizing the fundamental structure of nervous systems.

Prediction of misfolded proteins spreading in Alzheimer's disease using machine learning and spreading models

The pervasive impact of Alzheimer's disease on aging society represents one of the main challenges at this time. Current investigations highlight 2 specific misfolded proteins in its development: Amyloid-$\beta$ and tau. Previous studies focused on spreading for misfolded proteins exploited simulations, which required several parameters to be empirically estimated. Here, we provide an alternative view based on 2 machine learning approaches which we compare with known simulation models. The first approach applies an autoregressive model constrained by structural connectivity, while the second is based on graph convolutional networks. The aim is to predict concentrations of Amyloid-$\beta$ 2 yr after a provided baseline. We also evaluate its real-world effectiveness and suitability by providing a web service for physicians and researchers. In experiments, the autoregressive model generally outperformed state-of-the-art models resulting in lower prediction errors. While it is important to note that a comprehensive prognostic plan cannot solely rely on amyloid beta concentrations, their prediction, achieved by the discussed approaches, can be valuable for planning therapies and other cures, especially when dealing with asymptomatic patients for whom novel therapies could prove effective.

Multiclass characterization of frontotemporal dementia variants via multimodal brain network computational inference

Characterizing a particular neurodegenerative condition against others possible diseases remains a challenge along clinical, biomarker, and neuroscientific levels. This is the particular case of frontotemporal dementia (FTD) variants, where their specific characterization requires high levels of expertise and multidisciplinary teams to subtly distinguish among similar physiopathological processes. Here, we used a computational approach of multimodal brain networks to address simultaneous multiclass classification of 298 subjects (one group against all others), including five FTD variants: behavioral variant FTD, corticobasal syndrome, nonfluent variant primary progressive aphasia, progressive supranuclear palsy, and semantic variant primary progressive aphasia, with healthy controls. Fourteen machine learning classifiers were trained with functional and structural connectivity metrics calculated through different methods. Due to the large number of variables, dimensionality was reduced, employing statistical comparisons and progressive elimination to assess feature stability under nested cross-validation. The machine learning performance was measured through the area under the receiver operating characteristic curves, reaching 0.81 on average, with a standard deviation of 0.09. Furthermore, the contributions of demographic and cognitive data were also assessed via multifeatured classifiers. An accurate simultaneous multiclass classification of each FTD variant against other variants and controls was obtained based on the selection of an optimum set of features. The classifiers incorporating the brain's network and cognitive assessment increased performance metrics. Multimodal classifiers evidenced specific variants' compromise, across modalities and methods through feature importance analysis. If replicated and validated, this approach may help to support clinical decision tools aimed to detect specific affectations in the context of overlapping diseases.