Search

BackgroundPrevious studies have classified major depression and healthy control groups based on vocal acoustic features, but the classification accuracy needs to be improved. Therefore, this study utilized deep learning methods to construct classification and prediction models for major depression and healthy control groups.Methods120 participants aged 16–25 participated in this study, included 64 MDD group and 56 HC group. We used the Covarep open-source algorithm to extract a total of 1200 high-level statistical functions for each sample. In addition, we used Python for correlation analysis, and neural network to establish the model to distinguish whether participants experienced depression, predict the total depression score, and evaluate the effectiveness of the classification and prediction model.ResultsThe classification modelling of the major depression and the healthy control groups by relevant and significant vocal acoustic features was 0.90, and the Receiver Operating Characteristic (ROC) curves analysis results showed that the classification accuracy was 84.16%, the sensitivity was 95.38%, and the specificity was 70.9%. The depression prediction model of speech characteristics showed that the predicted score was closely related to the total score of 17 items of the Hamilton Depression Scale(HAMD-17) (r=0.687, P

BackgroundDepression is a widespread mental disorder that affects a significant portion of the population. However, the assessment of depression is often subjective, relying on standard questions or interviews. Acoustic features have been suggested as a reliable and objective alternative for depression assessment. Therefore, in this study, we aim to identify and explore voice acoustic features that can effectively and rapidly predict the severity of depression, as well as investigate the potential correlation between specific treatment options and voice acoustic features.MethodsWe utilized voice acoustic features correlated with depression scores to train a prediction model based on artificial neural network. Leave-one-out cross-validation was performed to evaluate the performance of the model. We also conducted a longitudinal study to analyze the correlation between the improvement of depression and changes in voice acoustic features after an Internet-based cognitive-behavioral therapy (ICBT) program consisting of 12 sessions.ResultsOur study showed that the neural network model trained based on the 30 voice acoustic features significantly correlated with HAMD scores can accurately predict the severity of depression with an absolute mean error of 3.137 and a correlation coefficient of 0.684. Furthermore, four out of the 30 features significantly decreased after ICBT, indicating their potential correlation with specific treatment options and significant improvement in depression (p

Objective: Alcohol use disorder (AUD) is a serious issue worldwide and frequently co-occurs with depression. However, the quality of life (QOL) of AUD patients with and without depression is not well studied in the Chinese Han population. The aim of this study was to investigate QOL and its correlates in AUD patients with and without depression in China.Methods: Five hundred and fifteen psychiatric patients diagnosed with AUD were recruited. All these patients completed the Beck Depression Inventory (BDI) to assess depression, the Medical Outcome Study 36-Item Short Form Health Survey (SF-36) to evaluate QOL and the Alcohol Use Disorders Identification Test (AUDIT) to measure the severity of drinking.Results: Compared with AUD patients without depression, those with depression had a lower QOL in all eight domains of the SF-36 (all P < 0.001), but were more willing to have alcohol-related treatment (P < 0.05). Negative correlations were noted between (i) the BDI total score and all eight domains of the SF-36 (all P < 0.001); and (ii) between the AUDIT total score and six domains of the SF-36 (all P < 0.05).Conclusions: Depression impairs QOL in patients with AUD in China. Early intervention in comorbid depression to improve QOL is needed.

Bipolar II disorder (BD-II) major depression episode is highly associated with suicidality, and objective neural biomarkers could be key elements to assist in early prevention and intervention. This study aimed to integrate altered brain functionality in the frontolimbic system and machine learning techniques to classify suicidal BD-II patients and predict suicidality risk at the individual level. A cohort of 169 participants were enrolled, including 43 BD-II depression patients with at least one suicide attempt during a current depressive episode (SA), 62 BD-II depression patients without a history of attempted suicide (NSA), and 64 demographically matched healthy controls (HCs). We compared resting-state functional connectivity (rsFC) in the frontolimbic system among the three groups and explored the correlation between abnormal rsFCs and the level of suicide risk (assessed using the Nurses' Global Assessment of Suicide Risk, NGASR) in SA patients. Then, we applied support vector machines (SVMs) to classify SA vs. NSA in BD-II patients and predicted the risk of suicidality. SA patients showed significantly decreased frontolimbic rsFCs compared to NSA patients. The left amygdala-right middle frontal gyrus (orbital part) rsFC was negatively correlated with NGASR in the SA group, but not the severity of depressive or anxiety symptoms. Using frontolimbic rsFCs as features, the SVMs obtained an overall 84% classification accuracy in distinguishing SA and NSA. A significant correlation was observed between the SVMs-predicted NGASR and clinical assessed NGASR (r = 0.51, p = 0.001). Our results demonstrated that decreased rsFCs in the frontolimbic system might be critical objective features of suicidality in BD-II patients, and could be useful for objective prediction of suicidality risk in individuals.

BackgroundDepressive symptoms are common among psychiatric patients with alcohol dependence (AD). However, the prevalence and clinical correlates of comorbid depressive symptoms are less well studied in Chinese Han patients.MethodsIn this hospital-based survey, we recruited 378 psychiatric patients diagnosed with AD according to the Diagnostic and Statistical Manual of Mental Disorders-Fourth Edition (DSM-IV). All patients completed the Beck Depression Inventory (BDI) to evaluate depressive symptoms and the Alcohol Use Disorders Identification Test (AUDIT) to assess the severity of drinking.ResultsCompared to patients without depressive symptoms, 48.9% (185/378) of the patients with comorbid depressive symptoms were younger, had a more unstable marital status, had a higher AUDIT total score, and had a higher adverse consequences subscore (all P < 0.05). Further logistic regression analysis showed that unstable marital status (Odds ratios [OR] = 2.20, 95% confidence interval [CI] 1.21–3.99) and AUDIT total score (OR=1.07, 95% CI 1.03–1.11) were significantly associated with depressive symptoms.ConclusionsOur findings indicate high comorbidity between AD and depressive symptoms in Chinese psychiatric patients. Moreover, some variables are correlates of comorbid depressive symptoms. Particular attention should be paid to the early detection and intervention for this comorbid condition and its risk factors.

Background: Major depressive disorders often involve somatic symptoms and have been found to have fundamental differences from non-somatic depression (NSD). However, the neural basis of this type of somatic depression (SD) is unclear. The aim of this study is to use the amplitude of low-frequency fluctuation (ALFF) and functional connectivity (FC) analyses to examine the abnormal, regional, spontaneous, neuronal activity and the corresponding brain circuits in SD patients.Methods: 35 SD patients, 25 NSD patients, and 27 matched healthy controls were selected to complete this study. The ALFF and seed-based FC analyses were employed, and the Pearson correlation was determined to observe possible clinical relevance.Results: Compared with NSD, the SD group showed a significant ALFF increase in the right inferior temporal gyrus; a significant ALFF decrease in left hippocampus, right inferior frontal orbital gyrus and left thalamus; and a significant decrease in the FC value between the right inferior frontal orbital gyrus and the left inferior parietal cortex (p < 0.05, corrected). Within the SD group, the mean ALFF value of the right inferior frontal orbital gyrus was associated with the anxiety factor scores (r = –0.431, p = 0.010, corrected).Conclusions: Our findings suggest that abnormal differences in the regional spontaneous neuronal activity of the right inferior frontal orbital gyrus were associated with dysfunction patterns of the corresponding brain circuits during rest in SD patients, including the limbic-cortical systems and the default mode network. This may be an important aspect of the underlying mechanisms for pathogenesis of SD at the neural level.