Predicting depression and anxiety of Chinese population during COVID-19 in psychological evaluation data by XGBoost.

BACKGROUND: Due to the onset of sudden stress, COVID-19 has greatly impacted the incidence of depression and anxiety. However, challenges still exist in identifying high-risk groups for depression and anxiety during COVID-19. Studies have identified how resilience and social support can be employed as effective predictors of depression and anxiety. This study aims to select the best combination of variables from measures of resilience, social support, and alexithymia for predicting depression and anxiety. METHODS: The eXtreme Gradient Boosting (XGBoost1) model was applied to a dataset including data on 29,841 participants that was collected during the COVID-19 pandemic. Discriminant analyses on groups of participants with depression (DE2), anxiety (AN3), comorbid depression and anxiety (DA4), and healthy controls (HC5), were performed. All variables were selected according to their importance for classification. Further, analyses were performed with selected features to determine the best variable combination. RESULTS: The mean accuracies achieved by three classification tasks, DE vs HC, AN vs HC, and DA vs HC, were 0.78, 0.77, and 0.89. Further, the combination of 19 selected features almost exhibited the same performance as all 56 variables (accuracies = 0.75, 0.75, and 0.86). CONCLUSIONS: Resilience, social support, and some demographic data can accurately distinguish DE, AN, and DA from HC. The results can be used to inform screening practices for depression and anxiety. Additionally, the model performance of a limited scale including only 19 features indicates that using a simplified scale is feasible.

The Impact of School Education on Depressive Symptoms in Chinese Adolescents: a Prospective Longitudinal Study.

There is a growing but limited literature on psychological distress among Chinese students, especially the impact of the COVID-19 pandemic, using a longitudinal comparison between in school and at home. This study aimed to assess the psychological status of adolescents in school and related risk and protective factors. We surveyed 13,637 adolescents before the COVID-19 outbreak (T1) and 10,216 after two months of home confinement (T2). The 9-item Patient Health Questionnaire (PHQ-9) was used to assess depressive symptoms or the severity of depression among the adolescents. In addition, the Childhood Trauma Questionnaire and the Connor-Davidson Resilience Scales were also used to screen for experiences of abuse and neglect and to measure resilience in adolescents. At baseline, 22.34% reported depressive symptoms. At T2, this rate decreased to 14.86%. When adolescents were in school, age (P < .0001), gender (P < .0001), and experience of abuse (P < .0001) were risk factors, while parent-child relationship (P < .0001), and resilience (P < .0001) were protective factors for depressive symptoms. After leaving school, age and physical abuse were no longer risk factors for depression. The negative impact of school education on the mental health of adolescents in China exceeds even the impact of the pandemic and home isolation. The focus should be on those adolescents with abuse experience and poor parent-child relationships to prevent the onset of psychological and psychiatric disorders.

Symptoms of Anxiety and Depression Among Adolescents Before vs During COVID-19-Related School Closures in China.

This cohort study compares the psychological status of Chinese adolescents at school before the COVID-19 pandemic and at home during the pandemic to assess whether school attendance was associated with negative mental health outcomes.

Self-help cognitive behavioral therapy application for COVID-19-related mental health problems: A longitudinal trial.

BACKGROUND AND AIM: Recently, the availability and usefulness of mobile self-help mental health applications have increased, but few applications deal with COVID-19-related psychological problems. This study explored the intervention efficacy of a mobile application on addressing psychological problems related to COVID-19. METHODS: A longitudinal control trial involving 129 Chinese participants with depression symptoms was conducted through the mobile application "Care for Your Mental Health and Sleep during COVID-19" (CMSC) based on WeChat. Participants were divided into two groups: mobile internet cognitive behavioral therapy (MiCBT) and wait-list. The primary outcome was improvement in depression symptoms. Secondary outcomes included improvement in anxiety and insomnia. The MiCBT group received three self-help CBT intervention sessions in one week via CMSC. RESULTS: The MiCBT group showed significant improvement in depression and insomnia (allP < 0.05) compared with the wait-list group. Although both groups showed significant improvement in anxiety at the intervention's end, compared with the wait-list group, the MiCBT group had no significant advantage. Correlation analysis showed that improvement in depression and anxiety had a significant positive association with education level. Changes in insomnia were significantly negatively correlated with anxiety of COVID-19 at the baseline. CMSC was considered helpful (n=68, 81.9 %) and enjoyable (n=54, 65.9 %) in relieving depression and insomnia during the COVID-19 outbreak. CONCLUSIONS: CMSC is verified to be effective and convenient for improving COVID-19-related depression and insomnia symptoms. A large study with sufficient evidence is required to determine its continuous effect on reducing mental health problems during the pandemic.