Aim: This study aims to develop new approaches to characterize brain networks to potentially contribute to a better understanding of mechanisms involved in depression. Method and subjects: We recruited 90 subjects: 49 healthy controls (HC) and 41 patients with a major depressive episode (MDE). All subjects underwent clinical evaluation and functional resting-state MRI. The data were processed investigating functional connectivity network measures across the two groups using Brain Connectivity Toolbox. The statistical inferences were developed at a functional network level, using a false discovery rate method. Linear discriminant analysis was used to differentiate between the two groups. Results and discussion: Significant differences in functional connectivity (FC) between depressed patients vs. healthy controls was demonstrated, with brain regions including the lingual gyrus, cerebellum, midcingulate cortex and thalamus more prominent in healthy subjects as compared to depression where the orbitofrontal cortex emerged as a key node. Linear discriminant analysis demonstrated that full-connectivity matrices were the most precise in differentiating between depression vs. health subjects. Conclusion: The study provides supportive evidence for impaired functional connectivity networks in MDE patients.

We address the interpretability of the machine learning algorithm in the context of the relevant problem of discriminating between patients with major depressive disorder (MDD) and healthy controls using functional networks derived from resting-state functional magnetic resonance imaging data. We applied linear discriminant analysis (LDA) to the data from 35 MDD patients and 50 healthy controls to discriminate between the two groups utilizing functional networks’ global measures as the features. We proposed the combined approach for feature selection based on statistical methods and the wrapper-type algorithm. This approach revealed that the groups are indistinguishable in the univariate feature space but become distinguishable in a three-dimensional feature space formed by the identified most important features: mean node strength, clustering coefficient, and the number of edges. LDA achieves the highest accuracy when considering the network with all connections or only the strongest ones. Our approach allowed us to analyze the separability of classes in the multidimensional feature space, which is critical for interpreting the results of machine learning models. We demonstrated that the parametric planes of the control and MDD groups rotate in the feature space with increasing the thresholding parameter and that their intersection increases with approaching the threshold of 0.45, for which classification accuracy is minimal. Overall, the combined approach for feature selection provides an effective and interpretable scenario for discriminating between MDD patients and healthy controls using measures of functional connectivity networks. This approach can be applied to other machine learning tasks to achieve high accuracy while ensuring the interpretability of the results.

We constructed a novel design integrating the administration of a clinical self-assessment scale with simultaneous acquisition of functional Magnetic Resonance Imaging (fMRI), aiming at cross-validation between psychopathology evaluation and neuroimaging techniques. We hypothesized that areas demonstrating differential activation in two groups of patients (the first group exhibiting paranoid delusions in the context of paranoid schizophrenia—SCH—and second group with a depressive episode in the context of major depressive disorder or bipolar disorder—DEP) will have distinct connectivity patterns and structural differences. Fifty-one patients with SCH (n = 25) or DEP (n = 26) were scanned with three different MRI sequences: a structural and two functional sequences—resting-state and task-related fMRI (the stimuli represent items from a paranoid-depressive self-evaluation scale). While no significant differences were found in gray matter volumes, we were able to discriminate between the two clinical entities by identifying two significant clusters of activations in the SCH group—the left Precuneus (PreCu) extending to the left Posterior Cingulate Cortex (PCC) and the right Angular Gyrus (AG). Additionally, the effective connectivity of the middle frontal gyrus (MFG), a part of the Dorsolateral Prefrontal Cortex (DLPFC) to the Anterior Insula (AI), demonstrated a significant difference between the two groups with inhibitory connection demonstrated only in SCH. The observed activations of PreCu, PCC, and AG (involved in the Default Mode Network DMN) might be indirect evidence of the inhibitory connection from the DLPFC to AI, interfering with the balancing function of the insula as the dynamic switch in the DMN. The findings of our current study might suggest that the connectivity from DLPFC to the anterior insula can be interpreted as evidence for the presence of an aberrant network that leads to behavioral abnormalities, the manifestation of which depends on the direction of influence. The reduced effective connectivity from the AI to the DLPFC is manifested as depressive symptoms, and the inhibitory effect from the DLPFC to the AI is reflected in the paranoid symptoms of schizophrenia.

We present a novel method for analyzing brain functional networks using functional magnetic resonance imaging data, which involves utilizing consensus networks. In this study, we compare our approach to a standard group-based method for patients diagnosed with major depressive disorder (MDD) and a healthy control group, taking into account different levels of connectivity. Our findings demonstrate that the consensus network approach uncovers distinct characteristics in network measures and degree distributions when considering connection strengths. In the healthy control group, as connection strengths increase, we observe a transition in the network topology from a combination of scale-free and random topologies to a small-world topology. Conversely, the MDD group exhibits uncertainty in weak connections, while strong connections display small-world properties. In contrast, the group-based approach does not exhibit significant differences in behavior between the two groups. However, it does indicate a transition in topology from a scale-free-like structure to a combination of small-world and scale-free topologies. The use of the consensus network approach also holds immense potential for the classification of MDD patients, as it unveils substantial distinctions between the two groups.