Deep neural network for prediction of diet quality among doctors and nurses in North China during the COVID-19 pandemic.

Objective: The COVID-19 pandemic has placed unprecedented pressure on front-line healthcare workers, leading to poor health status, especially diet quality. This study aimed to develop a diet quality prediction model and determine the predictive effects of personality traits, socioeconomic status, lifestyles, and individual and working conditions on diet quality among doctors and nurses during the COVID-19 pandemic. Methods: A total of 5,013 doctors and nurses from thirty-nine COVID-19 designated hospitals provided valid responses in north China in 2022. Participants' data related to social-demographic characteristics, lifestyles, sleep quality, personality traits, burnout, work-related conflicts, and diet quality were collected with questionnaires. Deep Neural Network (DNN) was applied to develop a diet quality prediction model among doctors and nurses during the COVID-19 pandemic. Results: The mean score of diet quality was 46.14 ± 15.08; specifically, the mean scores for variety, adequacy, moderation, and overall balance were 14.33 ± 3.65, 17.99 ± 5.73, 9.41 ± 7.33, and 4.41 ± 2.98, respectively. The current study developed a DNN model with a 21-30-28-1 network framework for diet quality prediction. The DNN model achieved high prediction efficacy, and values of R2, MAE, MSE, and RMSE were 0.928, 0.048, 0.004, and 0.065, respectively. Among doctors and nurses in north China, the top five predictors in the diet quality prediction model were BMI, poor sleep quality, work-family conflict, negative emotional eating, and nutrition knowledge. Conclusion: During the COVID-19 pandemic, poor diet quality is prevalent among doctors and nurses in north China. Machine learning models can provide an automated identification mechanism for the prediction of diet quality. This study suggests that integrated interventions can be a promising approach to improving diet quality among doctors and nurses, particularly weight management, sleep quality improvement, work-family balance, decreased emotional eating, and increased nutrition knowledge.

Machine-learning prediction of BMI change among doctors and nurses in North China during the COVID-19 pandemic.

Objective: The COVID-19 pandemic has become a major public health concern over the past 3 years, leading to adverse effects on front-line healthcare workers. This study aimed to develop a Body Mass Index (BMI) change prediction model among doctors and nurses in North China during the COVID-19 pandemic, and further identified the predicting effects of lifestyles, sleep quality, work-related conditions, and personality traits on BMI change. Methods: The present study was a cross-sectional study conducted in North China, during May-August 2022. A total of 5,400 doctors and nurses were randomly recruited from 39 COVID-19 designated hospitals and 5,271 participants provided valid responses. Participants' data related to social-demographics, dietary behavior, lifestyle, sleep, personality, and work-related conflicts were collected with questionnaires. Deep Neural Network (DNN) was applied to develop a BMI change prediction model among doctors and nurses during the COVID-19 pandemic. Results: Of participants, only 2,216 (42.0%) individuals kept a stable BMI. Results showed that personality traits, dietary behaviors, lifestyles, sleep quality, burnout, and work-related conditions had effects on the BMI change among doctors and nurses. The prediction model for BMI change was developed with a 33-26-20-1 network framework. The DNN model achieved high prediction efficacy, and values of R 2, MAE, MSE, and RMSE for the model were 0.940, 0.027, 0.002, and 0.038, respectively. Among doctors and nurses, the top five predictors in the BMI change prediction model were unbalanced nutritional diet, poor sleep quality, work-family conflict, lack of exercise, and soft drinks consumption. Conclusion: During the COVID-19 pandemic, BMI change was highly prevalent among doctors and nurses in North China. Machine learning models can provide an automated identification mechanism for the prediction of BMI change. Personality traits, dietary behaviors, lifestyles, sleep quality, burnout, and work-related conditions have contributed to the BMI change prediction. Integrated treatment measures should be taken in the management of weight and BMI by policymakers, hospital administrators, and healthcare workers.

Factors Influencing Post-traumatic Stress Symptoms in Chinese Adolescents During the COVID-19 Pandemic.

To investigate the prevalence of post-traumatic stress symptoms (PTSSs) and analyze the influencing factors of PTSS among adolescents in a large sample study during the COVID-19 pandemic, we did a cross-sectional study by collecting demographic data and mental health measurements from a large group of 175,318 adolescents in 32 Chinese provinces and autonomous regions, using the Impact of Event Scale-Revised (IES-R) that was used to measure the PTSS of the participants. The results showed that the prevalence of PTSS was 35.7% in Chinese adolescents during the COVID-19 pandemic. Binary logistic regression analysis showed that, for the personal risk factors, the older age, female gender, the personality domains of extroversion, the irregular sleep schedule, the lack of aerobic exercise, and the lack of peer support were associated with the higher levels of PTSS. The family subjective and objective factors were associated with higher levels of PTSS. Our findings suggested that family factors are the most important factors that affect Chinese adolescents' PTSS due to the longtime home quarantine.

Psychological Impact of COVID-19 Epidemic on Adolescents: A Large Sample Study in China.

Background: The COVID-19 pandemic is a major public health emergency. However, little is known about the psychological impact of this pandemic on adolescents. We aim to assess the prevalence and influencing factors of depression, anxiety, and posttraumatic growth (PTG) among adolescents in a large sample study. Methods: This cross-sectional study collected demographic data and mental health measurements from 175,416 adolescents covering 31 provinces, centrally administered municipalities, and autonomous regions in mainland China from February 23 to March 8, 2020. The status of depression, anxiety, and PTG was assessed by the nine-item Patient Health Questionnaire, seven-item generalized anxiety disorder questionnaire, and post-traumatic growth inventory. Results: The prevalence of depression, anxiety, and PTG in adolescents was 35.9, 28.0, and 45.6%, respectively. The prevalence of depression and anxiety in the slight or severe epidemic areas was similar. Regression analysis showed that female sex and older age were associated with higher levels of depression, anxiety, and lower levels of PTG. Symptoms related to COVID-19, excessive attention to epidemic information, living in urban or severe epidemic areas, and conflicts with parents during home quarantine were risk factors for depression, anxiety, and PTG. Frequent communication with peers, exercise, and receiving public welfare psychological assistance were protective factors. Poor family economic status was a significant risk factor for depression and PTG. Conclusion: Our findings suggested that positive and negative psychological reactions coexist in adolescents faced with the pandemic. The factors associated with psychological problems and PTG provide strategic guidance for maintaining adolescents' mental health in China and worldwide during any pandemic such as COVID-19.

Perceived Stress and Smartphone Addiction in Medical College Students: The Mediating Role of Negative Emotions and the Moderating Role of Psychological Capital.

Background: Many studies have confirmed the existence of an extremely close relationship between smartphone addiction and perceived stress. However, the mediating and moderating mechanisms underlying the association between perceived stress and smartphone addiction in medical college students remain largely unexplored. Methods: A questionnaire was distributed among a total of 769 medical college students in Heilongjiang Province, China. Participants completed measures of perceived stress, smartphone addiction, negative emotions, and psychological capital. Pearson's correlation analysis was used to test the correlations between variables. The analysis of a moderated mediation model was performed using Hayes's PROCESS macro. Results: Pearson's correlation analysis indicated that perceived stress (r = 0.18, p < 0.01) and negative emotions (r = 0.31, p < 0.01) were positively correlated with smartphone addiction, and psychological capital was negatively correlated with smartphone addiction (r = -0.29, p < 0.01). The moderated mediation analysis indicated that negative emotions partially mediated the association between perceived stress and smartphone addiction [mediation effect accounted for 33.3%, SE = 0.10, 95% CI = (0.10, 0.24)], and the first stage of the mediation process was significantly moderated by psychological capital [moderated mediation = -0.01, SE = 0.01, 95% CI = (-0.01, -0.00)]. Conclusion: Negative emotions play a mediating role between perceived stress and smartphone addiction, and psychological capital plays an important moderating role in the first stage of the mediation process.

Roles of Anxiety and Depression in Predicting Cardiovascular Disease Among Patients With Type 2 Diabetes Mellitus: A Machine Learning Approach.

Cardiovascular disease (CVD) is a major complication of type 2 diabetes mellitus (T2DM). In addition to traditional risk factors, psychological determinants play an important role in CVD risk. This study applied Deep Neural Network (DNN) to develop a CVD risk prediction model and explored the bio-psycho-social contributors to the CVD risk among patients with T2DM. From 2017 to 2020, 834 patients with T2DM were recruited from the Department of Endocrinology, Affiliated Hospital of Harbin Medical University, China. In this cross-sectional study, the patients' bio-psycho-social information was collected through clinical examinations and questionnaires. The dataset was randomly split into a 75% train set and a 25% test set. DNN was implemented at the best performance on the train set and applied on the test set. The receiver operating characteristic curve (ROC) analysis was used to evaluate the model performance. Of participants, 272 (32.6%) were diagnosed with CVD. The developed ensemble model for CVD risk achieved an area under curve score of 0.91, accuracy of 87.50%, sensitivity of 88.06%, and specificity of 87.23%. Among patients with T2DM, the top five predictors in the CVD risk model were body mass index, anxiety, depression, total cholesterol, and systolic blood pressure. In summary, machine learning models can provide an automated identification mechanism for patients at CVD risk. Integrated treatment measures should be taken in health management, including clinical care, mental health improvement, and health behavior promotion.

The Impact of Transformational Leadership on Physicians' Performance in China: A Cross-Level Mediation Model.

Transformational leadership has been becoming increasingly vital to the provision of high-quality health care, particularly during major public health emergencies. The present study aims to investigate the impact of transformational leadership on physicians' performance and explore the cross-level underlying mechanisms with achievement motivations and coping styles among Chinese physicians. During 2017-2019, 1,527 physicians of 101 departments were recruited from six hospitals in China with a cluster random sampling method. Participants completed several questionnaires regarding their job performance, achievement motivations, coping styles, and transformational leadership. Multilevel mediation effects were tested using cross-level path analysis. The result of this study indicated that transformational leadership was applied well in Chinese medical settings with a score of 101.56 ± 6.42. The hierarchical linear model showed that transformational leadership had a cross-level direct positive effect on physicians' performance (ß = 1.524, p < 0.05). Furthermore, results of cross-level path analyses revealed that transformational leadership contributed to physicians' performance by sequentially influencing achievement motivations first and then coping styles. In addition, the path "transformational leadership → positive coping (PC) style → physicians' performance" showed the strongest cross-level indirect effect. In summary, public health leaders should enhance physicians' performance by promoting individual development, especially achievement motivation and PC style.

Social Support and Suicide Risk Among Chinese University Students: A Mental Health Perspective.

Background: World Health Organization recognizes suicide as a public health priority. This study aimed to investigate the risk life events which led university students to consider suicide and explore the protective mechanism of social support (including subjective support, objective support, and support utilization) on suicide risk. Methods: Three thousand nine hundred and seventy-two university students were recruited in Harbin, China. Social Support Rating Scale, Self-Rating Anxiety Scale, the Beck Depression Inventory, and the 25-item scale of suicide acceptability were used to collect participants' information. Descriptive statistics, Pearson's correlation, and mediation analysis were employed for statistical analysis. Results: "Drug addict," "infected with HIV," and "incurable illness" were the top three events that led university students to consider suicide. Social support played an important protective role against suicide risk. Subjective support and support utilization had total effects on suicide acceptability, including direct and indirect effects. Anxiety (indirect effect = -0.022, 95% CI = -0.037 ~ -0.009) and depressive symptoms (indirect effect = -0.197, 95% CI = -0.228 ~ -0.163) mediated the relationship between subjective support and suicide acceptability; meanwhile, the association between support utilization and suicide acceptability was mediated by anxiety (indirect effect = -0.054, 95% CI = -0.088 ~ -0.024) and depressive symptoms (indirect effect = -0.486, 95% CI = -0.558 ~ -0.422). However, the protective impact of objective support worked totally through decreasing anxiety (indirect effect = -0.018, 95% CI = -0.035 ~ -0.006) and depressive symptoms (indirect effect = -0.196, 95% CI = -0.246 ~ -0.143). Moreover, the mediation effects of depressive symptoms had stronger power than anxiety in the impact of social support on suicide risk. Conclusions: Among Chinese university students, suicide acceptability was elevated when there was a health scare. Social support effectively reduced suicide risk via decreasing anxiety and depressive symptoms. From the mental health perspective, families, peers, teachers, and communities should work together to establish a better social support system for university students, if necessary, help them to seek professional psychological services.