Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Tian Z

PROVIDER: S-EPMC9710109 | biostudies-literature | 2023 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Tian Zhanxiao Z Qu Wei W Zhao Yanli Y Zhu Xiaolin X Wang Zhiren Z Tan Yunlong Y Jiang Ronghuan R Tan Shuping S

Journal of affective disorders 20221130

<h4>Background</h4>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 depres ...[more]

PMID: 36462608

Similar Datasets

Project description:BackgroundEvidence on associations between COVID-19 illness and mental health is mixed. We aimed to examine whether COVID-19 is associated with deterioration in mental health while considering pre-pandemic mental health, time since infection, subgroup differences, and confirmation of infection via self-reported test and serology data.MethodsWe obtained data from 11 UK longitudinal studies with repeated measures of mental health (psychological distress, depression, anxiety, and life satisfaction; mental health scales were standardised within each study across time) and COVID-19 status between April, 2020, and April, 2021. We included participants with information available on at least one mental health outcome measure and self-reported COVID-19 status (suspected or test-confirmed) during the pandemic, and a subset with serology-confirmed COVID-19. Furthermore, only participants who had available data on a minimum set of covariates, including age, sex, and pre-pandemic mental health were included. We investigated associations between having ever had COVID-19 and mental health outcomes using generalised estimating equations. We examined whether associations varied by age, sex, ethnicity, education, and pre-pandemic mental health, whether the strength of the association varied according to time since infection, and whether associations differed between self-reported versus confirmed (by test or serology) infection.FindingsBetween 21 Dec, 2021, and July 11, 2022, we analysed data from 54 442 participants (ranging from a minimum age of 16 years in one study to a maximum category of 90 years and older in another; including 33 200 [61·0%] women and 21 242 [39·0%] men) from 11 longitudinal UK studies. Of 40 819 participants with available ethnicity data, 36 802 (90·2%) were White. Pooled estimates of standardised differences in outcomes suggested associations between COVID-19 and subsequent psychological distress (0·10 [95% CI 0·06 to 0·13], I2=42·8%), depression (0·08 [0·05 to 0·10], I2=20·8%), anxiety (0·08 [0·05 to 0·10], I2=0·0%), and lower life satisfaction (-0·06 [-0·08 to -0·04], I2=29·2%). We found no evidence of interactions between COVID-19 and sex, education, ethnicity, or pre-pandemic mental health. Associations did not vary substantially between time since infection of less than 4 weeks, 4-12 weeks, and more than 12 weeks, and were present in all age groups, with some evidence of stronger effects in those aged 50 years and older. Participants who self-reported COVID-19 but had negative serology had worse mental health outcomes for all measures than those without COVID-19 based on serology and self-report. Participants who had positive serology but did not self-report COVID-19 did not show association with mental health outcomes.InterpretationSelf-reporting COVID-19 was longitudinally associated with deterioration in mental health and life satisfaction. Our findings emphasise the need for greater post-infection mental health service provision, given the substantial prevalence of COVID-19 in the UK and worldwide.FundingUK Medical Research Council and UK National Institute for Health and Care Research.

Project description:Background: Depression and anxiety are leading causes of disability worldwide but often remain undetected and untreated. Smartphone and wearable devices may offer a unique source of data to detect moment by moment changes in risk factors associated with mental disorders that overcome many of the limitations of traditional screening methods. Objective: The current study aimed to explore the extent to which data from smartphone and wearable devices could predict symptoms of depression and anxiety. Methods: A total of N = 60 adults (ages 24-68) who owned an Apple iPhone and Oura Ring were recruited online over a 2-week period. At the beginning of the study, participants installed the Delphi data acquisition app on their smartphone. The app continuously monitored participants' location (using GPS) and smartphone usage behavior (total usage time and frequency of use). The Oura Ring provided measures related to activity (step count and metabolic equivalent for task), sleep (total sleep time, sleep onset latency, wake after sleep onset and time in bed) and heart rate variability (HRV). In addition, participants were prompted to report their daily mood (valence and arousal). Participants completed self-reported assessments of depression, anxiety and stress (DASS-21) at baseline, midpoint and the end of the study. Results: Multilevel models demonstrated a significant negative association between the variability of locations visited and symptoms of depression (beta = -0.21, p = 0.037) and significant positive associations between total sleep time and depression (beta = 0.24, p = 0.023), time in bed and depression (beta = 0.26, p = 0.020), wake after sleep onset and anxiety (beta = 0.23, p = 0.035) and HRV and anxiety (beta = 0.26, p = 0.035). A combined model of smartphone and wearable features and self-reported mood provided the strongest prediction of depression. Conclusion: The current findings demonstrate that wearable devices may provide valuable sources of data in predicting symptoms of depression and anxiety, most notably data related to common measures of sleep.

Project description:IntroductionWith the number of menopausal women projected estimated to reach 1.2 billion by 2030 worldwide, it is critically important to understand how menopause may affect women's emotional well-being and how many women are affected by this. This study aimed to explore (i) the relationship between psychological complaints (depression, anxiety, poor memory) across different menopausal stages and (ii) investigate the correlation between resilience, self-efficacy, and perceived stress levels, with psychological complaints and whether this was associated with menopausal stage and/or age.Methods287 respondents completed the Menopausal Quality of Life (MenQoL), Perceived Stress Scale (PSS-10), Brief Resilience Scale (BRS), and General Self-efficacy (GSE) scales. Parametric and non-parametric analysis were used to analyse how bothered women were by self-reported poor memory and feelings of depression and anxiety, alongside perceived stress, resilience, and self-efficacy between women in different menopausal stages using STRAW criteria. The association between protective factors (self-efficacy and resilience) and psychological complaints was analysed with partial correlation analysis controlling for menopausal stages and/or age.ResultsA significant difference was found between the levels of perceived stress, and how bothered women were by feelings of depression and anxiety between early-perimenopausal and post-menopausal women. However, with the inclusion of age as a covariate, menopausal stage no longer predicted the level of self-reported stress and anxiety in menopausal women. There was also no difference between poor self-reported memory, or of self-efficacy or resilience between women in different menopausal stages. However, self-efficacy and resilience were associated with how bothered women were by feelings of depression and anxiety, and the experience of stress. Stress was the only variable to be associated with poor self-reported memory independent of age and/or menopausal status.DiscussionEarly perimenopausal women experienced the highest level of stress and were more severely bothered by feelings of depression and anxiety, with the poorest overall self-reported psychosocial quality of life. Post-menopausal women, however, reported to have similar experiences as premenopausal women. Age explained the associations between menopausal stage, stress and anxiety, but not between depression and different menopausal stages. Resilience and self-efficacy were associated with psychological complaints independent of menopausal stage and age, suggesting that therapies focusing on increasing resilience and self-efficacy may be beneficial to help target these psychological complaints at any time.

Dataset Information

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

Background

Methods

Results

Conclusions

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets