A comprehensive analysis of resting state fMRI measures to classify individual patients with Alzheimer's disease

Abstract

Alzheimer's disease (AD) patients show altered patterns of functional connectivity (FC) on resting state functional magnetic resonance imaging (RSfMRI) scans. It is yet unclear which RSfMRI measures are most informative for the individual classification of AD patients. We investigated this using RSfMRI scans from 77 AD patients (MMSE = 20.4 ± 4.5) and 173 controls (MMSE = 27.5 ± 1.8). We calculated i) FC matrices between resting state components as obtained with independent component analysis (ICA), ii) the dynamics of these FC matrices using a sliding window approach, iii) the graph properties (e.g., connection degree, and clustering coefficient) of the FC matrices, and iv) we distinguished five FC states and administered how long each subject resided in each of these five states. Furthermore, for each voxel we calculated v) FC with 10 resting state networks using dual regression, vi) FC with the hippocampus, vii) eigenvector centrality, and viii) the amplitude of low frequency fluctuations (ALFF). These eight measures were used separately as predictors in an elastic net logistic regression, and combined in a group lasso logistic regression model. We calculated the area under the receiver operating characteristic curve plots (AUC) to determine classification performance. The AUC values ranged between 0.51 and 0.84 and the highest were found for the FC matrices (0.82), FC dynamics (0.84) and ALFF (0.82). The combination of all measures resulted in an AUC of 0.85. We show that it is possible to obtain moderate to good AD classification using RSfMRI scans. FC matrices, FC dynamics and ALFF are most discriminative and the combination of all the resting state measures improves classification accuracy slightly.

Network‐targeted approach and postoperative resting‐state functional magnetic resonance imaging are associated with seizure outcome

“…Advancements have been made in image acquisition and capacity to algorithmically sort images trained by a constellation of image and patient features. 56,57 Difficulties with learning, cognition, depression, or anxiety are well-recognized comorbidities of epilepsy. 47 Thus, it is unclear to what extent this could improve upon expert interpretation.…”

Gaussian Graphical Models Reveal Inter-Modal and Inter-Regional Conditional Dependencies of Brain Alterations in Alzheimer's Disease

“…GGMs were recently applied as clustering algorithm for brain networks in a few other single-modality applications. De Vos et al [de Vos et al, 2017] found them useful for increasing group separation between AD and controls compared to classical Pearson correlation networks in resting-state functional connectivity. Titov et al [Titov et al, 2017] compared metabolic networks for the differential diagnosis between AD and frontotemporal lobar degeneration (FTLD).…”

Bootstrapping promotes the RSFC-behavior associations: an application of individual cognitive traits prediction

“…Jiang et al, 2019;Santarnecchi et al, 2014) and chronological age (Dosenbach et al, 2010;Liem et al, 2017). To model the RSFC-phenotype association, three prediction models including connectome-based predictive modeling (CPM), support vector regression (SVR) and least absolute shrinkage and selection operator (LASSO) have been frequently adopted for their good performances and interpretabilities (Coloigner et al, 2016;de Vos et al, 2018;R. Jiang et al, 2019;Meng et al, 2017;Ryali et al, 2012;Shen et al, 2017).…”