Prediction of the efficacy of group cognitive behavioral therapy using heart rate variability based smart wearable devices: a randomized controlled study.

BACKGROUND: Depression and anxiety are common and disabling mental health problems in children and young adults. Group cognitive behavioral therapy (GCBT) is considered that an efficient and effective treatment for these significant public health concerns, but not all participants respond equally well. The aim of this study was to examine the predictive ability of heart rate variability (HRV), based on sensor data from consumer-grade wearable devices to detect GCBT effectiveness in early intervention. METHODS: In a study of 33 college students with depression and anxiety, participants were randomly assigned to either GCBT group or a wait-list control (WLC) group. They wore smart wearable devices to measure their physiological activities and signals in daily life. The HRV parameters were calculated and compared between the groups. The study also assessed correlations between participants' symptoms, HRV, and GCBT outcomes. RESULTS: The study showed that participants in GCBT had significant improvement in depression and anxiety symptoms after four weeks. Higher HRV was associated with greater improvement in depressive and anxious symptoms following GCBT. Additionally, HRV played a noteworthy role in determining how effective GCBT was in improve anxiety(P = 0.002) and depression(P = 0.020), and its predictive power remained significant even when considering other factors. CONCLUSION: HRV may be a useful predictor of GCBT treatment efficacy. Identifying predictors of treatment response can help personalize treatment and improve outcomes for individuals with depression and anxiety. TRIAL REGISTRATION: The trial has been retrospectively registered on [22/06/2023] with the registration number [NCT05913349] in the ClinicalTrials.gov. Variations in heart rate variability (HRV) have been associated with depression and anxiety, but the relationship of baseline HRV to treatment outcome in depression and anxiety is unclear. This study predicted GCBT effectiveness using HRV measured by wearable devices. 33 students with depression and anxiety participated in a trial comparing GCBT and wait-list control. HRV parameters from wearables correlated with symptoms (PHQ, PSS) and GCBT effectiveness. Baseline HRV levels are strongly associated with GCBT treatment outcomes. HRV may serve as a useful predictor of efficacy of GCBT treatment,facilitating personalized treatment approaches for individuals with depression and anxiety.

Effectiveness of a Biofeedback Intervention Targeting Mental and Physical Health Among College Students Through Speech and Physiology as Biomarkers Using Machine Learning: A Randomized Controlled Trial.

Biofeedback therapy is mainly based on the analysis of physiological features to improve an individual's affective state. There are insufficient objective indicators to assess symptom improvement after biofeedback. In addition to psychological and physiological features, speech features can precisely convey information about emotions. The use of speech features can improve the objectivity of psychiatric assessments. Therefore, biofeedback based on subjective symptom scales, objective speech, and physiological features to evaluate efficacy provides a new approach for early screening and treatment of emotional problems in college students. A 4-week, randomized, controlled, parallel biofeedback therapy study was conducted with college students with symptoms of anxiety or depression. Speech samples, physiological samples, and clinical symptoms were collected at baseline and at the end of treatment, and the extracted speech features and physiological features were used for between-group comparisons and correlation analyses between the biofeedback and wait-list groups. Based on the speech features with differences between the biofeedback intervention and wait-list groups, an artificial neural network was used to predict the therapeutic effect and response after biofeedback therapy. Through biofeedback therapy, improvements in depression (p = 0.001), anxiety (p = 0.001), insomnia (p = 0.013), and stress (p = 0.004) severity were observed in college-going students (n = 52). The speech and physiological features in the biofeedback group also changed significantly compared to the waitlist group (n = 52) and were related to the change in symptoms. The energy parameters and Mel-Frequency Cepstral Coefficients (MFCC) of speech features can predict whether biofeedback intervention effectively improves anxiety and insomnia symptoms and treatment response. The accuracy of the classification model built using the artificial neural network (ANN) for treatment response and non-response was approximately 60%. The results of this study provide valuable information about biofeedback in improving the mental health of college-going students. The study identified speech features, such as the energy parameters, and MFCC as more accurate and objective indicators for tracking biofeedback therapy response and predicting efficacy. Trial Registration ClinicalTrials.gov ChiCTR2100045542.

Sex-specific immune-inflammatory markers and lipoprotein profile in patients with anhedonia with unipolar and bipolar depression.

BACKGROUND: Anhedonia is a core symptom in patients with unipolar and bipolar depression. However, sex-specific markers reflecting biological heterogeneity are lacking. Emerging evidence suggests that sex differences in immune-inflammatory markers and lipoprotein profiles are associated with anhedonia. METHODS: The demographic and clinical data, immune-inflammatory markers (CD3, CD4, and CD8), and lipoprotein profiles [TC, TG, LDL-C, HDL-C, lipoprotein(a) Lp (a)] of 227 patients with unipolar and bipolar depression were collected. The Hamilton Depression Rating Scale (HAMD) and Snaith-Hamilton Pleasure Scale (SHAPS) were used to assess depression and anhedonia symptoms. Data were analyzed using ANOVA, logistic regression, and receiver operating characteristic curves. RESULTS: Male patients in the anhedonia group had higher levels of CD3, CD4, and CD8, and lower levels of Lp (a) than the non-anhedonia group, while no significant difference was identified in female patients with and without anhedonia. Logistic regression analysis showed that CD3, CD4, CD8, and Lp (a) levels were associated with anhedonia in male patients. Furthermore, the combination of CD3, CD4, CD8, and Lp (a) had the strongest predictive value for distinguishing anhedonia in male patients than individual parameters. CONCLUSIONS: We identified sex-specific associations between immune-inflammatory markers, lipoprotein profiles, and anhedonia in patients with unipolar and bipolar depression. The combination of CD3, CD4, CD8, and Lp (a) might be a possible biomarker for identifying anhedonia in male patients with unipolar and bipolar depression.

Latent class analysis of depression and anxiety among medical students during COVID-19 epidemic.

OBJECTIVE: The novel coronavirus disease 2019 (COVID-19) is a global public health emergency that has caused worldwide concern. The mental health of medical students under the COVID-19 epidemic has attracted much attention. This study aims to identify subgroups of medical students based on depression and anxiety and explore the influencing factors during the COVID-19 epidemic in China. METHODS: A total of 29,663 medical students were recruited during the epidemic of COVID-19 in China. Depression and anxiety symptoms were assessed using Patient Health Questionnaire 9 (PHQ9) and Generalized Anxiety Disorder 7 (GAD7) respectively. Latent class analysis was performed based on depression and anxiety symptoms in medical students. The latent class subtypes were compared using the chi-square test. Multinomial logistic regression was used to examine associations between identified classes and related factors. RESULTS: In this study, three distinct subgroups were identified, namely, the poor mental health group, the mild mental health group and the low symptoms group. The number of medical students in each class is 4325, 9321 and 16,017 respectively. The multinomial logistic regression results showed that compared with the low symptoms group, the factors influencing depression and anxiety in the poor mental health group and mild mental health group were sex, educational level, drinking, individual psychiatric disorders, family psychiatric disorders, knowledge of COVID-19, fear of being infected, and participate in mental health education on COVID-19. CONCLUSIONS: Our findings suggested that latent class analysis can be used to categorize different medical students according to their depression and anxiety symptoms during the outbreak of COVID-19. The main factors influencing the poor mental health group and the mild mental health group are basic demographic characteristics, disease history, COVID-19 related factors and behavioural lifestyle. School administrative departments can carry out targeted psychological counseling according to different subgroups to promote the physical and mental health of medical students.

Exploring the relationship between response time sequence in scale answering process and severity of insomnia: A machine learning approach.

Utilizing computer-based scales for cognitive and psychological evaluations allows for the collection of objective data, such as response time. This cross-sectional study investigates the significance of response time data in cognitive and psychological measures, with a specific focus on its role in evaluating sleep quality through the Insomnia Severity Index (ISI) scale. A mobile application was designed to administer scale tests and collect response time data from 2729 participants. We explored the relationship between symptom severity and response time. A machine learning model was developed to predict the presence of insomnia symptoms in participants using response time data. The result revealed a statistically significant difference (p < 0.01) in the total response time between participants with or without insomnia symptom. Furthermore, a strong correlation was observed between the severity of specific insomnia aspects and the response times at the individual questions level. The machine learning model demonstrated a high predictive Area Under the ROC Curve (AUROC) of 0.824 in predicting insomnia symptoms based on response time data. These findings highlight the potential utility of response time data to evaluate cognitive and psychological measures.

Enhanced classification and severity prediction of major depressive disorder using acoustic features and machine learning.

Background: Previous 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. Methods: 120 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. Results: The 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<0.01); and the Mean Absolute Error(MAE) between the model's predicted score and total HAMD-17 score was 4.51. Limitation: This study's results may have been influenced by anxiety comorbidities. Conclusion: The vocal acoustic features can not only effectively classify the major depression and the healthy control groups, but also accurately predict the severity of depressive symptoms.

Temporal dynamics in psychological assessments: a novel dataset with scales and response times.

The growing prevalence of mental health issues underscores the need for innovative screening methods. Large-scale, internet-based psychological screening has emerged as a vital tool to accurately determine morbidity rates and facilitate early diagnosis of mental disorders. However, conventional psychological screening methods often struggle with non-genuine responses and lack objective metrics. To bridge this gap, we have compiled a novel dataset derived from an expansive screening initiative at Xinxiang Medical University. The study, conducted from February 27 to March 17, 2021, yielded a dataset comprising responses from 24,292 students to four well-established psychological scales-PHQ-9, GAD-7, ISI, and PSS. A distinctive feature of this dataset is the inclusion of response time data, which captures the temporal dynamics of participants' interactions with the scales, offering valuable insights into their response behaviour. The release of this dataset offers a substantial opportunity for researchers in the domains of psychology and public health to explore new insights into mental health, scale reliability, and the dynamics of psychological assessment.

Digital Dietary Behaviors in Individuals With Depression: Real-World Behavioral Observation.

BACKGROUND: Depression is often accompanied by changes in behavior, including dietary behaviors. The relationship between dietary behaviors and depression has been widely studied, yet previous research has relied on self-reported data which is subject to recall bias. Electronic device-based behavioral monitoring offers the potential for objective, real-time data collection of a large amount of continuous, long-term behavior data in naturalistic settings. OBJECTIVE: The study aims to characterize digital dietary behaviors in depression, and to determine whether these behaviors could be used to detect depression. METHODS: A total of 3310 students (2222 healthy controls [HCs], 916 with mild depression, and 172 with moderate-severe depression) were recruited for the study of their dietary behaviors via electronic records over a 1-month period, and depression severity was assessed in the middle of the month. The differences in dietary behaviors across the HCs, mild depression, and moderate-severe depression were determined by ANCOVA (analyses of covariance) with age, gender, BMI, and educational level as covariates. Multivariate logistic regression analyses were used to examine the association between dietary behaviors and depression severity. Support vector machine analysis was used to determine whether changes in dietary behaviors could detect mild and moderate-severe depression. RESULTS: The study found that individuals with moderate-severe depression had more irregular eating patterns, more fluctuated feeding times, spent more money on dinner, less diverse food choices, as well as eating breakfast less frequently, and preferred to eat only lunch and dinner, compared with HCs. Moderate-severe depression was found to be negatively associated with the daily 3 regular meals pattern (breakfast-lunch-dinner pattern; OR 0.467, 95% CI 0.239-0.912), and mild depression was positively associated with daily lunch and dinner pattern (OR 1.460, 95% CI 1.016-2.100). These changes in digital dietary behaviors were able to detect mild and moderate-severe depression (accuracy=0.53, precision=0.60), with better accuracy for detecting moderate-severe depression (accuracy=0.67, precision=0.64). CONCLUSIONS: This is the first study to develop a profile of changes in digital dietary behaviors in individuals with depression using real-world behavioral monitoring. The results suggest that digital markers may be a promising approach for detecting depression.

Factor structure of the patient health questionnaire-9 and measurement invariance across gender and age among Chinese university students.

The Patient Health Questionnaire-9 (PHQ-9) has been widely used to screen depression symptoms. The present research aimed to assess the reliability and validity of PHQ-9, besides measurement invariance of the PHQ-9 across gender and age among Chinese university students. A total of 12,957 Chinese college students from 2 universities in Henan and Hainan provinces (China) completed the questionnaires via WeChat. This research reported the psychometric properties of PHQ-9 and measurement invariance of the PHQ-9 across gender and age among Chinese university students. Compared with 1-factor model, the 2-factor (affective factor and somatic factor) model of PHQ-9 showed a better fit index in Chinese university students. Without the last 2 items, the 2-factor model of the PHQ-9 showed satisfactory reliability, validity, and good fit index (e.g., Root mean square error of approximation = 0.060, Goodness-of-fit index = 0.982, Comparative fit index = 0.986, and Tucker-Lewis index = 0.974). The Cronbach's alpha of PHQ-9 was 0.874. Multi-group analysis across gender and age demonstrated that measurement equivalency for the 2-factor model of the PHQ-9 was established (e.g., Root mean square error of approximation < 0.08, Comparative fit index > 0.90 and Tucker-Lewis index > 0.90). The 2-factor model of the PHQ-9 without the items of "movement" and "desire to die" showed a better fit index in Chinese university students. The measurement equivalence across gender and age for the 2-factor model of the PHQ-9 can be established among Chinese university students.

Fast and accurate assessment of depression based on voice acoustic features: a cross-sectional and longitudinal study.

Background: Depression 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. Methods: We 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. Results: Our 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 < 0.05). Conclusion: Voice acoustic features can effectively and rapidly predict the severity of depression, providing a low-cost and efficient method for screening patients with depression on a large scale. Our study also identified potential acoustic features that may be significantly related to specific treatment options for depression.

Association between perceived stress and depression among medical students during the outbreak of COVID-19: The mediating role of insomnia.

BACKGROUND: The purpose of this study was to explore the association between perceived stress and depression among medical students and the mediating role of insomnia in this relationship during the COVID-19 pandemic in China. METHODS: A cross-sectional survey was conducted from March to April 2020 in medical university. Levels of perceived stress, insomnia and depression were measured using Perceived Stress Scale (PSS), Insomnia Severity Index (ISI) and Patient Health Questionnaire 9 (PHQ-9). The descriptive analyses of the demographic characteristics and correlation analyses of the three variables were calculated. The significance of the mediation effect was obtained using a bootstrap approach with SPSS PROCESS macro. RESULTS: The mean age of medical students was 21.46 years (SD=2.50). Of these medical students, 10,185 (34.3%) were male and 19,478 (65.7%) were female. Perceived stress was significantly associated with depression (ß=0.513, P < 0.001). Insomnia mediated the association between perceived stress and depression (ß=0.513, P < 0.001). The results of the non-parametric bootstrapping method confirmed the significance of the indirect effect of perceived stress through insomnia (95% bootstrap CI =0.137, 0.149). The indirect effect of insomnia accounted for 44.13% of the total variance in depression. CONCLUSIONS: These findings contribute to a better understanding of the interactive mechanisms underlying perceived stress and depression, and elucidating the mediating effects of insomnia on the association. This research provides a useful theoretical and methodological approach for prevention of depression in medical students. Findings from this study indicated that it may be effective to reduce depression among medical students by improving sleep quality and easing perceived stress.

Cholesterol and triglyceride levels in first-episode patients with major depressive disorder: A meta-analysis of case-control studies.

BACKGROUND: Lipid profile disturbances are frequently observed in major depressive disorder (MDD) and constitute to high mortality rates. However, less is known about whether this risk is present in patients with first-episode MDD. Therefore, this meta-analysis was conducted to examine if lipid parameters differed between healthy controls and first-episode MDD patients. METHODS: Cochrane Library, PubMed, PsycINFO, EMBASE, Chinese Journal Net, and WanFang databases were searched from inception to October 23, 2018. The primary outcomes were triglycerides, high-density lipoprotein (HDL) cholesterol, low-density lipoprotein (LDL) cholesterol, and total cholesterol levels. RESULTS: A total of 11 case-control studies compared 690 subjects with first-episode MDD and 614 healthy controls were included and analyzed. Compared to healthy controls, patients with first-episode MDD were significantly associated with higher triglyceride (SMD = 0.29, 95% CI: 0.09, 0.48, P = 0.004) and lower HDL cholesterol levels (SMD = -0.54, 95% CI: -0.86, -0.22, P = 0.001). Subgroup analyses revealed that first-episode MDD patients with higher triglyceride and lower HDL levels were found only in Chinese and plasma group when compared to healthy controls (P < 0.05). Meta-regression analysis showed that the significant heterogeneity for triglyceride and HDL cholesterol was partly explained by the quality of study. No significant difference was found in LDL cholesterol and total cholesterol levels between the two groups. LIMITATIONS: Heterogeneity was relatively high among the included studies. CONCLUSIONS: Elevated triglyceride and decreased HDL cholesterol levels may be associated with first-episode MDD. Findings support early lipid monitoring and interventions targeting healthy lifestyle.

Prognostic and clinicopathological significance of neutrophil-to-lymphocyte ratio in patients with oral cancer.

Objectives: Many studies have examined the prognostic significance of the neutrophil-to-lymphocyte ratio (NLR) in oral cancer; however, the results are contradictory. We, therefore, conducted a meta-analysis aiming to clarify the prognostic value of the NLR in oral cancer patients. Methods: A literature search was conducted in the PubMed, Web of Science, and Embase databases. Stata version 12.0 was used for statistical analysis. Results: A total of 14 studies with 3216 patients were finally included. The results indicated that a high NLR was significantly associated with worse DFS (n=10, HR = 1.73, 95% confidence interval [CI] = 1.44-2.07, P<0.001). Similar results were observed for overall survival (OS) (n=9, HR = 1.61, 95% CI = 1.39-1.86, P<0.001). Moreover, a high NLR was also correlated with lymph node metastasis (n=7, odds ratio [OR] = 1.62, 95% CI = 1.32-1.98, P<0.001), advanced tumor stage (n=7, OR = 2.63, 95% CI = 2.12-3.25, P<0.001), T stage (n=6, OR = 3.22, 95% CI = 2.59-4.01, P<0.001), tumor differentiation (n=5, OR = 1.48, 95% CI = 1.03-2.11, P=0.033), and perineural invasion (n=4, OR = 1.83, 95% CI = 1.4-2.39, P<0.001). However, an elevated NLR was not correlated with gender. Conclusion: This meta-analysis showed that the NLR might be a potential independent prognostic factor in patients with oral cancer.