Subject-specific features of excitation/inhibition profiles in neurodegenerative diseases

Abstract

Brain pathologies are characterized by microscopic changes in neurons and synapses that reverberate into large scale networks altering brain dynamics and functional states. An important yet unresolved issue concerns the impact of patients' excitation/inhibition profiles on neurodegenerative diseases including Alzheimer's Disease, Frontotemporal Dementia, and Amyotrophic Lateral Sclerosis. In this work, we used The Virtual Brain (TVB) simulation platform to simulate brain dynamics in healthy and neurodegenerative conditions and to extract information about the excitatory/inhibitory balance in single subjects. The brain structural and functional connectomes were extracted from 3T-MRI (Magnetic Resonance Imaging) scans and TVB nodes were represented by a Wong-Wang neural mass model endowing an explicit representation of the excitatory/inhibitory balance. Simulations were performed including both cerebral and cerebellar nodes and their structural connections to explore cerebellar impact on brain dynamics generation. The potential for clinical translation of TVB derived biophysical parameters was assessed by exploring their association with patients' cognitive performance and testing their discriminative power between clinical conditions. Our results showed that TVB biophysical parameters differed between clinical phenotypes, predicting higher global coupling and inhibition in Alzheimer's Disease and stronger N-methyl-D-aspartate (NMDA) receptor-dependent excitation in Amyotrophic Lateral Sclerosis. These physio-pathological parameters allowed us to perform an advanced analysis of patients' conditions. In backward regressions, TVB-derived parameters significantly contributed to explain the variation of neuropsychological scores and, in discriminant analysis, the combination of TVB parameters and neuropsychological scores significantly improved the discriminative power between clinical conditions. Moreover, cluster analysis provided a unique description of the excitatory/inhibitory balance in individual patients. Importantly, the integration of cerebro-cerebellar loops in simulations improved TVB predictive power, i.e., the correlation between experimental and simulated functional connectivity in all pathological conditions supporting the cerebellar role in brain function disrupted by neurodegeneration. Overall, TVB simulations reveal differences in the excitatory/inhibitory balance of individual patients that, combined with cognitive assessment, can promote the personalized diagnosis and therapy of neurodegenerative diseases.

Keywords: Alzheimer’s Disease; Amyotrophic Lateral Sclerosis; Frontotemporal Dementia; MRI; brain dynamics; connectivity; excitatory/inhibitory balance.

FIGURE 1

Schematic representation of modeling workflow. MRI is used to obtain the structural and experimental functional connectivity matrices (SC and expFC) needed for TVB construction and optimization. From top left, clockwise: diffusion weighted images are preprocessed and elaborated to yield whole-brain tractography. An ad hoc parcellation atlas combining AAL atlas and SUIT is used to map the SC matrices obtained from whole-brain tractography parcellation (top weight matrix, bottom distance matrix). The Virtual Brain (TVB) is constructed using the SC matrix for edges and neural masses for nodes. TVB simulations of neural activity allow to extract BOLD signals for each node leading to define the simulated functional connectivity (simFC) matrix. TVB optimization is performed through model inversion by comparing the simFC with the expFC. Model parameters, highlighted with circles, and the corresponding equations are shown at the bottom.

FIGURE 2

Networks connectivity matrices. Columns 1 and 2 show the experimental structural (SC) and functional connectivity (FC) matrices, which were used as input for TVB simulations in four different groups: healthy (HC), Alzheimer’s Disease (AD), Frontotemporal Dementia (FTD), and Amyotrophic Lateral Sclerosis (ALS). For each group, matrices of a randomly chosen subject are reported as an example. Columns 3–5 show the simulated FC obtained at single-subject level with three different networks: whole-brain, cortical subnetwork (Cerebral) and embedded cerebro-cerebellar subnetwork (Cerebro-Crbl). In the whole-brain network simulations were performed using whole-brain nodes and connections (whole-brain nodes and edges are colored); in the cortical subnetwork only cerebral cortex nodes and connections were considered (cortical nodes and edges are colored); in the embedded cerebro-cerebellar subnetwork cerebral cortex nodes were considered taking into account the influence of cerebro-cerebellar connections (cortical nodes and cerebellar edges are colored).

FIGURE 3

Boxplots of optimal biophysical parameters and Pearson correlation coefficients (PCC). (A) Boxplots of optimal biophysical parameters derived from TVB (global coupling, G, excitatory synaptic coupling, J_NMDA, local excitatory recurrence, w+, inhibitory synaptic coupling, Ji) across groups (Healthy Controls, Alzheimer’s Disease, Frontotemporal Dementia, and Amyotrophic Lateral Sclerosis). The asterisk (*) indicates a significant difference (Mann-Whitney, p < 0.05) between groups (see Table 2 for details). (B) Boxplots of Pearson correlation coefficients (PCC) between experimental and simulated FC for all groups (Healthy Controls, Alzheimer’s Disease, Frontotemporal Dementia, Amyotrophic Lateral Sclerosis) and networks (whole-brain network, Whole_brain, cortical subnetwork, cerebral; embedded cerebro-cerebellar subnetwork, Cerebro-Crbl). Asterisks (*) indicate a significant difference (p < 0.05) between networks (see Table 2 for details).

FIGURE 4

Classification analysis. ROC curves were calculated for each classification (Healthy Controls vs. Alzheimer’s Disease, Healthy Controls vs. Frontotemporal Dementia, Healthy Controls vs. Amyotrophic Lateral Sclerosis, Alzheimer’s Disease vs. Frontotemporal Dementia, Alzheimer’s Disease vs. Amyotrophic Lateral Sclerosis, Frontotemporal Dementia vs. Amyotrophic Lateral Sclerosis) with their corresponding groups of variables (TVB parameters alone, neuropsychological scores alone, TVB parameters combined with neuropsychological scores). AUC values confirmed that TVB parameters alone (blue) always yielded a poorer discriminant power than that offered by neuropsychological scores alone (green). The combination of TVB parameters with neuropsychological scores improved the discriminative power in all classifications reaching 100% when distinguishing between Alzheimer’s Disease and Healthy Controls and between Frontotemporal Dementia and Amyotrophic Lateral Sclerosis.

FIGURE 5

Excitation/inhibition profiles. (A) Each cluster was characterized by a typical excitation/inhibition profile. The color-bar (from blue to red) represents the scale from low to high of each TVB-derived biophysical parameter. (B) Visual representation of cluster distributions across groups (Healthy Controls, Alzheimer’s Disease, Frontotemporal Dementia, and Amyotrophic Lateral Sclerosis). Cluster numbers are reported on the x-axis while cluster frequencies in each condition are reported on the y-axis. Each dot represents a single subject.