Treatment Response Prediction for Major Depressive Disorder Patients via Multivariate Pattern Analysis of Thalamic Features.

Antidepressant treatment, as an important method in clinical practice, is not suitable for all major depressive disorder (MDD) patients. Although magnetic resonance imaging (MRI) studies have found thalamic abnormalities in MDD patients, it is not clear whether the features of the thalamus are suitable to serve as predictive aids for treatment responses at the individual level. Here, we tested the predictive value of gray matter density (GMD), gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and fractional ALFF (fALFF) of the thalamus using multivariate pattern analysis (MVPA). A total of 74 MDD patients and 44 healthy control (HC) subjects were recruited. Thirty-nine MDD patients and 35 HC subjects underwent scanning twice. Between the two scanning sessions, patients in the MDD group received selective serotonin reuptake inhibitor (SSRI) treatment for 3-month, and HC group did not receive any treatment. Gaussian process regression (GPR) was trained to predict the percentage decrease in the Hamilton Depression Scale (HAMD) score after treatment. The percentage decrease in HAMD score after SSRI treatment was predicted by building GPRs trained with baseline thalamic data. The results showed significant correlations between the true percentage of HAMD score decreases and predictions (p < 0.01, r 2 = 0.11) in GPRs trained with GMD. We did not find significant correlations between the true percentage of HAMD score decreases and predictions in GMV (p = 0.16, r 2 = 0.00), ALFF (p = 0.125, r 2 = 0.00), and fALFF (p = 0.485, r 2 = 0.10). Our results suggest that GMD of the thalamus has good potential as an aid in individualized treatment response predictions of MDD patients.

Effective Connectivity of Right Amygdala Subregions Predicts Symptom Improvement Following 12-Week Pharmacological Therapy in Major Depressive Disorder.

The low rates of treatment response still exist in the pharmacological therapy of major depressive disorder (MDD). Exploring an optimal neurological predictor of symptom improvement caused by pharmacotherapy is urgently needed for improving response to treatment. The amygdala is closely related to the pathological mechanism of MDD and is expected to be a predictor of the treatment. However, previous studies ignored the heterogeneousness and lateralization of amygdala. Therefore, this study mainly aimed to explore whether the right amygdala subregion function at baseline can predict symptom improvement after 12-week pharmacotherapy in MDD patients. We performed granger causality analysis (GCA) to identify abnormal effective connectivity (EC) of right amygdala subregions in MDD and compared the EC strength before and after 12-week pharmacological therapy. The results show that the abnormal EC mainly concentrated on the frontolimbic circuitry and default mode network (DMN). With relief of the clinical symptom, these abnormal ECs also change toward normalization. In addition, the EC strength of right amygdala subregions at baseline showed significant predictive ability for symptom improvement using a regularized least-squares regression predict model. These findings indicated that the EC of right amygdala subregions may be functionally related in symptom improvement of MDD. It may aid us to understand the neurological mechanism of pharmacotherapy and can be used as a promising predictor for symptom improvement in MDD.

Individualized diagnosis of major depressive disorder via multivariate pattern analysis of thalamic sMRI features.

BACKGROUND: Magnetic resonance imaging (MRI) studies have found thalamic abnormalities in major depressive disorder (MDD). Although there are significant differences in the structure and function of the thalamus between MDD patients and healthy controls (HCs) at the group level, it is not clear whether the structural and functional features of the thalamus are suitable for use as diagnostic prediction aids at the individual level. Here, we were to test the predictive value of gray matter density (GMD), gray matter volume (GMV), amplitude of low-frequency fluctuations (ALFF), and fractional amplitude of low-frequency fluctuations (fALFF) in the thalamus using multivariate pattern analysis (MVPA). METHODS: Seventy-four MDD patients and 44 HC subjects were recruited. The Gaussian process classifier (GPC) was trained to separate MDD patients from HCs, Gaussian process regression (GPR) was trained to predict depression scores, and Multiple Kernel Learning (MKL) was applied to explore the contribution of each subregion of the thalamus. RESULTS: The primary findings were as follows: [1] The balanced accuracy of the GPC trained with thalamic GMD was 96.59% (P < 0.001). The accuracy of the GPC trained with thalamic GMV was 93.18% (P < 0.001). The correlation between Hamilton Depression Scale (HAMD) score targets and predictions in the GPR trained with GMD was 0.90 (P < 0.001, r2 = 0.82), and in the GPR trained with GMV, the correlation between HAMD score targets and predictions was 0.89 (P < 0.001, r2 = 0.79). [2] The models trained with ALFF and fALFF in the thalamus failed to discriminate MDD patients from HC participants. [3] The MKL model showed that the left lateral prefrontal thalamus, the right caudal temporal thalamus, and the right sensory thalamus contribute more to the diagnostic classification. CONCLUSIONS: The results suggested that GMD and GMV, but not functional indicators of the thalamus, have good potential for the individualized diagnosis of MDD. Furthermore, the thalamus shows the heterogeneity in the structural features of thalamic subregions for predicting MDD. To our knowledge, this is the first study to focus on the thalamus for the prediction of MDD using machine learning methods at the individual level.

Gender context modulation on the self-enhancement effect of vocal attractiveness evaluation.

People evaluated their own voices as sounding more attractive than others rated their voices (i.e., self-enhancement effect from the perspective of the rater, termed "SE_rater"), and people also rated their own voices as more attractive than the voices of others (i.e., self-enhancement effect from the perspective of the voice, termed "SE_voice"). The aim of the present study is to explore whether the gender context (i.e., same-sex and opposite-sex rating context) could influence the SE effect of voice attractiveness evaluation. Male and female participants were asked to rate the attractiveness of their own voices and other participants' voices, either in a same-sex session or an opposite-sex session. The results demonstrated both the SE_rater and SE_voice effect in the same-sex and opposite-sex contexts, for both male and female. More importantly, we found that the SE_rater for the male voices was significantly greater than that for the female voices in the same-sex context whereas no such difference was found in the opposite-sex context. In addition, the SE_voice effect in men was larger in the same-sex context than that in the opposite-sex context whereas the SE_voice in women was smaller in the same-sex context than that in the opposite-sex context. These findings indicated that the self-enhancement effect of vocal attractiveness was modulated by the gender context.

Antidepressant Treatment-Induced State-Dependent Reconfiguration of Emotion Regulation Networks in Major Depressive Disorder.

Deficits in emotion regulation are the main clinical features, common risk factors, and treatment-related targets for major depressive disorder (MDD). The neural bases of emotion regulation are moving beyond specific functions and emphasizing instead the integrative functions of spatially distributed brain areas that work together as large-scale brain networks, but it is still unclear whether the dynamic interactions among these emotion networks would be the target of clinical intervention for MDD. Data were collected from 70 MDD patients and 43 sex- and age-matched healthy controls. The dynamic functional connectivity (dFC) between emotion regions was estimated via a sliding-window method based on resting-state functional magnetic resonance imaging (R-fMRI). A k-means clustering method was applied to classify all time windows across all participants into several dFC states reflecting recurring functional interaction patterns among emotion regions over time. The results showed that four dFC states were identified in the emotion networks. Their alterations of state-related occurrence proportion were found in MDD and subsequently normalized following 12-week antidepressant treatment. Baseline strong dFC could predict the reduction rate of Hamilton Depression Rating Scale (HAMD) scores. These findings highlighted the state-dependent reconfiguration of emotion regulation networks in MDD patients owing to antidepressant treatment.