Major depressive disorder (MDD) is a complex state-dependent psychiatric illness for which biomarkers linking psychophysical, biochemical, and psychopathological changes remain yet elusive, though. Earlier studies demonstrate reduced GABA in lower-order occipital cortex in acute MDD leaving open its validity and significance for higher-order visual perception, though. The goal of our study is to fill that gap by combining psychophysical investigation of visual perception with measurement of GABA concentration in middle temporal visual area (hMT+) in acute depressed MDD. Psychophysically, we observe a highly specific deficit in visual surround motion suppression in a large sample of acute MDD subjects which, importantly, correlates with symptom severity. Both visual deficit and its relation to symptom severity are replicated in the smaller MDD sample that received MRS. Using high-field 7T proton Magnetic resonance spectroscopy (1H-MRS), acute MDD subjects exhibit decreased GABA concentration in visual MT+ which, unlike in healthy subjects, no longer correlates with their visual motion performance, i.e., impaired SI. In sum, our combined psychophysical-biochemical study demonstrates an important role of reduced occipital GABA for altered visual perception and psychopathological symptoms in acute MDD. Bridging the gap from the biochemical level of occipital GABA over visual-perceptual changes to psychopathological symptoms, our findings point to the importance of the occipital cortex in acute depressed MDD including its role as candidate biomarker.

No abstract

Background: Depression is one of the most common psychological disorders nowadays, with continuous and prolonged low mood as the main clinical feature, and it is the most important type of psychological disorders in modern people. The aim of this study is to develop a depression prediction model based on causal inference and machine learning. Methods: This case study included 7000 subjects. A feature selection model was built based on a causal inference algorithm. The selected features were entered as variables in seven machine learning (ML) models built to create a predictive model for the diagnosis of depression. Results: Among the seven ML models, the random forest model (RF) showed the best performance. For the prediction of depression, the area under receiver operating characteristic (AUC) of the RF model was 0.908(0.810-1.00) in 10-fold stratified cross-validation and 0.901 (0.893-0.91) in external validation.

Amnestic mild cognitive impairment (aMCI) is a clinical subtype of MCI, which is known to have a high risk of developing Alzheimer’s disease (AD). Although neuroimaging studies have reported brain abnormalities in patients with aMCI, concurrent structural and functional patterns in patients with aMCI were still unclear. In this study, we combined voxel-based morphometry (VBM), amplitude of low-frequency fluctuations (ALFFs), regional homogeneity (Reho), and resting-state functional connectivity (RSFC) approaches to explore concurrent structural and functional alterations in patients with aMCI. We found that, compared with healthy controls (HCs), both ALFF and Reho were decreased in the right superior frontal gyrus (SFG_R) and right middle frontal gyrus (MFG_R) of patients with aMCI, and both gray matter volume (GMV) and Reho were decreased in the left inferior frontal gyrus (IFG_L) of patients with aMCI. Furthermore, we took these overlapping clusters from VBM, ALFF, and Reho analyses as seed regions to analyze RSFC. We found that, compared with HCs, patients with aMCI had decreased RSFC between SFG_R and the right temporal lobe (subgyral) (TL_R), the MFG_R seed and left superior temporal gyrus (STG_L), left inferior parietal lobule (IPL_L), and right anterior cingulate cortex (ACC_R), the IFG_L seed and left precentral gyrus (PRG_L), left cingulate gyrus (CG_L), and IPL_L. These findings highlighted shared imaging features in structural and functional magnetic resonance imaging (MRI), suggesting that SFG_R, MFG_R, and IFG_L may play a major role in the pathophysiology of aMCI, which might be useful to better understand the underlying neural mechanisms of aMCI and AD.