Changes in community structure of resting state functional connectivity in unipolar depression

Abstract

Major depression is a prevalent disorder that imposes a significant burden on society, yet objective laboratory-style tests to assist in diagnosis are lacking. We employed network-based analyses of "resting state" functional neuroimaging data to ascertain group differences in the endogenous cortical activity between healthy and depressed subjects.We additionally sought to use machine learning techniques to explore the ability of these network-based measures of resting state activity to provide diagnostic information for depression. Resting state fMRI data were acquired from twenty two depressed outpatients and twenty two healthy subjects matched for age and gender. These data were anatomically parcellated and functional connectivity matrices were then derived using the linear correlations between the BOLD signal fluctuations of all pairs of cortical and subcortical regions.We characterised the hierarchical organization of these matrices using network-based matrics, with an emphasis on their mid-scale "modularity" arrangement. Whilst whole brain measures of organization did not differ between groups, a significant rearrangement of their community structure was observed. Furthermore we were able to classify individuals with a high level of accuracy using a support vector machine, primarily through the use of a modularity-based metric known as the participation index.In conclusion, the application of machine learning techniques to features of resting state fMRI network activity shows promising potential to assist in the diagnosis of major depression, now suggesting the need for validation in independent data sets.

Figure 1. Correlation coefficients (a) uncorrected and (b) corrected for distance by the distance penalty equation (Appendix S1 A).

Entries marked in red denote bilateral connections between the same region, e.g. Hippocampus left and right.

Figure 2. Workflow for data processing, statistical testing and machine learning in this study.

All steps are described in detail in the methods section of this paper. Two analysis types were used, one for groupwise comparisons, and one for machine learning classification. The difference in modularity identification was selected so no groupwise information would influence the data used for machine learning. Thresholding and the calculation of all metrics with the exception of modularity was identical between the two analysis types.

Figure 3. Global metrics for subjects (blue) and healthy controls (red) across a range of thresholds for connectivity sparsity from 10% to 35% in 1% increments.

Inserts in each figure are the area under the curve (AUC) statistics for each metric.

Figure 4. Modular structure of one healthy individual, where brown, green, cyan, yellow and dark blue represent the 5 different modules.

Connections are drawn in the color of the modules if it connects nodes from the same modules, otherwise in black. Negative connections are marked in red. (a) is a fully connected graph, where correlation coefficients are modified by the distance penalty described in Appendix S1A, (b) and (c) have been thresholded to retain only 12% of edges.

Figure 5. ROIs that changed in rank order between HC and MDD (, FDR corrected).

Higher PI scores in the HC and MDD columns represent nodes which contain a higher porportion of connections within the module they belong to.

Figure 6. Global mean signal for healthy (left) and clinically depressed (right) subjects.

Figure 7. Top 25 features for classification using SVM obtained using mRMR.

Metrics included are participation index (PI), local/global efficiency (LE/GE), local efficiency (LE), degree (Deg) and betweenness centrality (BC).

Figure 8. Support vector machine classification algorithm using the top two features for segregation between groups.

Data points marked with an ‘x’ are used for training, while points marked as ‘o’ were used for testing.

Figure 9. Selectivity and specificity for support vector classification using a range of features.

Red line illustrates the cutoff chosen for this analysis.