Increasing depression patients puts great pressure on clinical diagnosis. Audio-based diagnosis is a helpful auxiliary tool for early mass screening. However, current methods consider only speech perception features, ignoring patients' vocal tract changes, which may partly result in the poor recognition. This work proposes a novel machine speech chain model for depression recognition (MSCDR) that can capture text-independent depressive speech representation from the speaker's mouth to the listener's ear to improve recognition performance. In the proposed MSCDR, linear predictive coding (LPC) and Mel-frequency cepstral coefficients (MFCC) features are extracted to describe the processes of speech generation and of speech perception, respectively. Then, a one-dimensional convolutional neural network and a long short-term memory network sequentially capture intra- and inter-segment dynamic depressive features for classification. We tested the MSCDR on two public datasets with different languages and paradigms, namely, the Distress Analysis Interview Corpus-Wizard of Oz and the Multi-modal Open Dataset for Mental-disorder Analysis. The accuracy of the MSCDR on the two datasets was 0.77 and 0.86, and the average F1 score was 0.75 and 0.86, which were better than the other existing methods. This improvement reveals the complementarity of speech production and perception features in carrying depressive information. The sample size was relatively small, which may limit the application in clinical translation to some extent. This experiment proves the good generalization ability and superiority of the proposed MSCDR and suggests that the vocal tract changes in patients with depression deserve attention for audio-based depression diagnosis.

Background: Subclinical depression (ScD) is a prevalent condition associated with relatively mild depressive states, and it poses a high risk of developing into major depressive disorder (MDD). However, the neural pathology of ScD is still largely unknown. Identifying the spontaneous neural activity involved in ScD may help clarify risk factors for MDD and explore treatment strategies for mild stages of depression. Methods: A total of 34 ScD subjects and 40 age-, sex-, and education-matched healthy controls were screened from 1105 college students. The amplitude of low-frequency fluctuation (ALFF) and regional homogeneity (ReHo) of resting-state fMRI were calculated to reveal neural activity. Strict statistical strategies, including Gaussian random field (GRF), false discovery rate (FDR), and permutation test (PT) with threshold-free cluster enhancement (TFCE), were conducted. Based on the altered ALFF and ReHo, resting-state functional connectivity (RSFC) was further analyzed using a seed-based approach. Results: The right precuneus and left middle frontal gyrus (MFG) both showed significantly increased ALFF and ReHo in ScD subjects. Moreover, the left hippocampus and superior frontal gyrus (SFG) showed decreased ALFF and increased ReHo, respectively. In addition, ScD subjects showed increased RSFC between MFG and hippocampus compared to healthy controls, and significant positive correlation was found between the Beck Depression Inventory-II (BDI-II) score and RSFC from MFG to hippocampus in ScD group. Conclusion: Spontaneous neural activities in the right precuneus, left MFG, SFG, and hippocampus were altered in ScD subjects. Functional alterations in these dorsolateral prefrontal cortex and default mode network regions are largely related to abnormal emotional processing in ScD, and indicate strong associations with brain impairments in MDD, which provide insight into potential pathophysiology mechanisms of subclinical depression.

Altered resting-state EEG activity has been repeatedly reported in major depressive disorder (MDD), but no robust biomarkers have been identified until now. The poor consistency of EEG alterations may be due to inconsistent resting conditions; that is, the eyes-open (EO) and eyes-closed (EC) conditions. Here, we explored the effect of the EO and EC conditions on EEG biomarkers for discriminating MDD subjects and healthy control (HC) subjects. EEG data were recorded from 30 first-episode MDD and 26 HC subjects during an 8-min resting-state session. The features were extracted using spectral power, Lempel–Ziv complexity, and detrended fluctuation analysis. Significant features were further selected via the sequential backward feature selection algorithm. Support vector machine (SVM), logistic regression, and linear discriminate analysis were used to determine a better resting condition to provide more reliable estimates for identifying MDD. Compared with the HC group, we found that the MDD group exhibited widespread increased $\beta $ and $\gamma $ powers ( ${p} < 0.01$ ) in both conditions. In the EO condition, the MDD group showed increased complexity and scaling exponents in the $\alpha $ band relative to HC subjects ( ${p} < 0.05$ ). The best classification performance of the combined feature sets was found in the EO condition, with the leave-one-out classification accuracy of 89.29%, sensitivity of 90.00%, and specificity of 88.46% using SVM with the linear kernel classifier when the threshold was set to 0.7, followed by the $\beta $ and $\gamma $ spectral features with an average accuracy of 83.93%. Overall, EO and EC conditions indeed affected the between-group variance, and the EO condition is suggested as the more separable resting condition to identify depression. Specially, the $\beta $ and $\gamma $ powers are suggested as potential biomarkers for first-episode MDD.

Gamma oscillations contribute to the pathogenesis mechanisms of major depressive disorder (MDD) have been proposed, but gamma activity is not well characterized. This study is the first attempt to investigate the altered gamma oscillations in first-episode MDD, particularly the beta-gamma coupling, and to determine the potential symptomatic relationship with the identified gamma dysregulation. Resting electroencephalography was recorded for 43 drug-naive first-episode MDD and 57 healthy control (HC) subjects. Integrated analysis of relative spectral power, weighted phase lag index, and phase-amplitude coupling (PAC) were utilized to reveal the alterations of gamma activities. Pearson's correlation was implemented to identify the relationship between altered gamma activities and the clinical depressive symptoms, which were categorized into four factors: anxiety somatization, retardation, cognitive disturbance, and sleep disturbance. Compared with HC subjects, MDD patients showed not only significantly decreased gamma powers in the left temporal and the bilateral occipital regions but also weakened gamma connectivity between the left hemisphere and the right frontal region. Furthermore, attenuated beta-gamma PAC of MDD patients was observed in the left temporal regions. Importantly, the suppression of left occipital mid- and high gamma oscillations were negatively correlated with sleep disturbance, while the deficits in left temporal beta-mid-gamma PAC and beta-high gamma PAC showed negative correlations with cognitive disturbance. Important limitations are the small sample size and the possible inclusion of bipolar depression in the MDD group. Our findings provide the first evidence that in first-episode MDD, aberrant gamma powers and beta-gamma coupling are associated with sleep and cognitive impairments, respectively, deepening our understanding of the physiological mechanisms underlying sleep and cognitive symptoms in first-episode MDD. Altered gamma oscillations emerge as promising biomarkers for diagnosing MDD.

The diagnosis of subclinical depression (SD) currently relies exclusively on subjective clinical scores and structured interviews, which shares great similarities with major depression (MD) and increases the risk of misdiagnosis of SD and MD. This study aimed to develop a method of disease classification for SD and MD by resting-state functional features using radiomics strategy. Twenty-six SD, 36 MD subjects and 33 well-matched healthy controls (HC) were recruited and underwent resting-state functional magnetic resonance imaging (rs-fMRI). A novel radiomics analysis was proposed to discriminate SD from MD. Multi-scale brain functional features were extracted to explore a comprehensive representation of functional characteristics. A two-level feature selection strategy and support vector machine (SVM) were employed for classification. The overall classification accuracy among SD, MD and HC groups was 84.21%. Particularly, the model excellently distinguished SD from MD with 96.77% accuracy, 100% sensitivity, and 92.31% specificity. Moreover, features with high discriminative power to distinguish SD from MD showed a strong association with default mode network, frontoparietal network, affective network, and visual network regions. The sample size was relatively small, which may limit the application in clinical translation to some extent. These findings demonstrated that a valid radiomics approach based on functional measures can discriminate SD from MD with a high classification performance, facilitating an objective and reliable diagnosis individually in clinical practice. Features with high discriminative power may provide insight into a profound understanding of the brain functional impairments and pathophysiology of SD and MD.

For decades, neuromodulation technology has demonstrated tremendous potential in the treatment of neuropsychiatric disorders. However, challenges such as being less intrusive, more concentrated, using less energy, and better public acceptance, must be considered. Several novel and optimized methods are thus urgently desiderated to overcome these barriers. In specific, temporally interfering (TI) electrical stimulation was pioneered in 2017, which used a low-frequency envelope waveform, generated by the superposition of two high-frequency sinusoidal currents of slightly different frequency, to stimulate specific targets inside the brain. TI electrical stimulation holds the advantages of both spatial targeting and non-invasive character. The ability to activate deep pathogenic targets without surgery is intriguing, and it is expected to be employed to treat some neurological or psychiatric disorders. Recently, efforts have been undertaken to investigate the stimulation qualities and translation application of TI electrical stimulation via computational modeling and animal experiments. This review detailed the most recent scientific developments in the field of TI electrical stimulation, with the goal of serving as a reference for future research.