Prediction of atmospheric pollutants in urban environment based on coupled deep learning model and sensitivity analysis.

Accurate and efficient predictions of pollutants in the atmosphere provide a reliable basis for the scientific management of atmospheric pollution. This study develops a model that combines an attention mechanism, convolutional neural network (CNN), and long short-term memory (LSTM) unit to predict the O3 and PM2.5 levels in the atmosphere, as well as an air quality index (AQI). The prediction results given by the proposed model are compared with those from CNN-LSTM and LSTM models as well as random forest and support vector regression models. The proposed model achieves a correlation coefficient between the predicted and observed values of more than 0.90, outperforming the other four models. The model errors are also consistently lower when using the proposed approach. Sobol-based sensitivity analysis is applied to identify the variables that make the greatest contribution to the model prediction results. Taking the COVID-19 outbreak as the time boundary, we find some homology in the interactions among the pollutants and meteorological factors in the atmosphere during different periods. Solar irradiance is the most important factor for O3, CO is the most important factor for PM2.5, and particulate matter has the most significant effect on AQI. The key influencing factors are the same over the whole phase and before the COVID-19 outbreak, indicating that the impact of COVID-19 restrictions on AQI gradually stabilized. Removing variables that contribute the least to the prediction results without affecting the model prediction performance improves the modeling efficiency and reduces the computational costs.

COVID-19 and common mental health symptoms in the early phase of the pandemic: An umbrella review of the evidence.

BACKGROUND: There remains uncertainty about the impact of the Coronavirus Disease 2019 (COVID-19) pandemic on mental health. This umbrella review provides a comprehensive overview of the association between the pandemic and common mental disorders. We qualitatively summarized evidence from reviews with meta-analyses of individual study-data in the general population, healthcare workers, and specific at-risk populations. METHODS AND FINDINGS: A systematic search was carried out in 5 databases for peer-reviewed systematic reviews with meta-analyses of prevalence of depression, anxiety, and post-traumatic stress disorder (PTSD) symptoms during the pandemic published between December 31, 2019 until August 12, 2022. We identified 123 reviews of which 7 provided standardized mean differences (SMDs) either from longitudinal pre- to during pandemic study-data or from cross-sectional study-data compared to matched pre-pandemic data. Methodological quality rated with the Assessment of Multiple Systematic Reviews checklist scores (AMSTAR 2) instrument was generally low to moderate. Small but significant increases of depression, anxiety, and/or general mental health symptoms were reported in the general population, in people with preexisting physical health conditions, and in children (3 reviews; SMDs ranged from 0.11 to 0.28). Mental health and depression symptoms significantly increased during periods of social restrictions (1 review; SMDs of 0.41 and 0.83, respectively) but anxiety symptoms did not (SMD: 0.26). Increases of depression symptoms were generally larger and longer-lasting during the pandemic (3 reviews; SMDs depression ranged from 0.16 to 0.23) than those of anxiety (2 reviews: SMDs 0.12 and 0.18). Females showed a significantly larger increase in anxiety symptoms than males (1 review: SMD 0.15). In healthcare workers, people with preexisting mental disorders, any patient group, children and adolescents, and in students, no significant differences from pre- to during pandemic were found (2 reviews; SMD's ranging from -0.16 to 0.48). In 116 reviews pooled cross-sectional prevalence rates of depression, anxiety, and PTSD symptoms ranged from 9% to 48% across populations. Although heterogeneity between studies was high and largely unexplained, assessment tools and cut-offs used, age, sex or gender, and COVID-19 exposure factors were found to be moderators in some reviews. The major limitations are the inability to quantify and explain the high heterogeneity across reviews included and the shortage of within-person data from multiple longitudinal studies. CONCLUSIONS: A small but consistent deterioration of mental health and particularly depression during early pandemic and during social restrictions has been found in the general population and in people with chronic somatic disorders. Also, associations between mental health and the pandemic were stronger in females and younger age groups than in others. Explanatory individual-level, COVID-19 exposure, and time-course factors were scarce and showed inconsistencies across reviews. For policy and research, repeated assessments of mental health in population panels including vulnerable individuals are recommended to respond to current and future health crises.

Risk of SARS-CoV-2 infection, severe COVID-19 illness and COVID-19 mortality in people with pre-existing mental disorders: an umbrella review.

INTRODUCTION: The COVID-19 pandemic has posed a serious health risk, especially in vulnerable populations. Even before the pandemic, people with mental disorders had worse physical health outcomes compared to the general population. This umbrella review investigated whether having a pre-pandemic mental disorder was associated with worse physical health outcomes due to the COVID-19 pandemic. METHODS: Following a pre-registered protocol available on the Open Science Framework platform, we searched Ovid MEDLINE All, Embase (Ovid), PsycINFO (Ovid), CINAHL, and Web of Science up to the 6th of October 2021 for systematic reviews on the impact of COVID-19 on people with pre-existing mental disorders. The following outcomes were considered: risk of contracting the SARS-CoV-2 infection, risk of severe illness, COVID-19 related mortality risk, risk of long-term physical symptoms after COVID-19. For meta-analyses, we considered adjusted odds ratio (OR) as effect size measure. Screening, data extraction and quality assessment with the AMSTAR 2 tool have been done in parallel and duplicate. RESULTS: We included five meta-analyses and four narrative reviews. The meta-analyses reported that people with any mental disorder had an increased risk of SARS-CoV-2 infection (OR: 1.71, 95% CI 1.09-2.69), severe illness course (OR from 1.32 to 1.77, 95%CI between 1.19-1.46 and 1.29-2.42, respectively) and COVID-19 related mortality (OR from 1.38 to 1.52, 95%CI between 1.15-1.65 and 1.20-1.93, respectively) as compared to the general population. People with anxiety disorders had an increased risk of SAR-CoV-2 infection, but not increased mortality. People with mood and schizophrenia spectrum disorders had an increased COVID-19 related mortality but without evidence of increased risk of severe COVID-19 illness. Narrative reviews were consistent with findings from the meta-analyses. DISCUSSION AND CONCLUSIONS: As compared to the general population, there is strong evidence showing that people with pre-existing mental disorders suffered from worse physical health outcomes due to the COVID-19 pandemic and may therefore be considered a risk group similar to people with underlying physical conditions. Factors likely involved include living accommodations with barriers to social distancing, cardiovascular comorbidities, psychotropic medications and difficulties in accessing high-intensity medical care.

Do COVID-19 pandemic-related behavior changes affect perioperative respiratory adverse events in children undergoing cardiac interventional catheterization?

BACKGROUND: The novel coronavirus disease (COVID-19) suddenly broke out in China in December 2019. Pandemic-related behavioral changes can cause perioperative respiratory adverse events in children with congenital heart disease (CHD). Here, we compared the incidence of perioperative respiratory adverse events (PRAEs) in CHD children with and without upper respiratory infection (URI) undergoing the cardiac catheterization before and during the COVID-19 pandemic. METHODS: This prospective observational single-center study was based at a tertiary care center in Shanghai, China. A total of 359 children with CHD with and without recent URI were included between January 2019 and March 2021. The overall incidence of PRAEs (laryngospasm, bronchospasm, coughing, airway secretion, airway obstruction, and oxygen desaturation) in non-URI and URI children undergoing elective cardiac catheterization was compared before and during the COVID-19 pandemic. A logistic regression model was fitted to identify the potential risk factors associated with PRAEs. RESULTS: Of the 564 children enrolled, 359 completed the study and were finally analyzed. The incidence of URIs decreased substantially during the COVID-19 pandemic (14% vs. 41%, P < 0.001). Meanwhile, the overall PRAEs also significantly declined regardless of whether the child had a recent URI (22.3% vs. 42.3%, P = 0.001 for non-URI and 29.2% vs. 58.7%, P = 0.012 for URI, respectively). Post-operative agitation in children without URI occurred less frequently during the pandemic than before (2.3% vs. 16.2%, P = 0.001). Behaviors before the COVID-19 pandemic (odds ratio = 2.84, 95% confidence interval [CI] 1.76-4.58) and recent URI (odds ratio = 1.79, 95% CI 1.09-2.92) were associated with PRAEs. CONCLUSIONS: COVID-19 pandemic-related behavioral changes were associated with a reduction in PRAEs in non-URI and URI children undergoing elective therapeutic cardiac catheterization.

Student COVID-19 vaccination preferences in China: A discrete choice experiment

Objective This study uses a discrete choice experiment (DCE) questionnaire to investigate student vaccination preferences for both intrinsic and extrinsic attributes. Methods A two-part DCE questionnaire was distributed to 1,138 students through face-to-face interviews at vaccination centers in Qingdao, China. Conditional logit models were used to understand student preference trade-offs. Mixed logit models (MLM) and sub-group analysis were conducted to understanding student preference heterogeneity. Results We found that students preferred vaccines with fewer side effects (β = 0.845;95% CI, 0.779–0.911), administered through third level health facilities (β = 0.170;95% CI, 0.110–0.230), and had at least 1 year duration of protection (β = 0.396;95% CI, 0.332–0.461. Higher perception of COVID-19 risks (β = 0.492;95% CI, 0.432–0.552) increased the likelihood of student vaccination uptake. Surprisingly, vaccine effectiveness (60%) and percentages of acquaintances vaccinated (60%) reduced vaccination utility, which points to free-rider problems. In addition, we find that student study majors did not contribute to preference heterogeneity, and the main disparities in preferences were attributed to student risk tolerances. Conclusion Both intrinsic and extrinsic attributes were influential factors shaping student preferences for COVID-19 vaccines. Our results inform universities and local governments across China on targeting their vaccination programs.

A Study of the Relationship between Corporate Culture and Corporate Sustainable Performance: Evidence from Chinese SMEs

Sustainable development is a significant issue facing small- and medium-sized enterprises (SMEs). Drawing on the literature of corporate sustainable development and the resource-based view, this study aims to examine how corporate flexibility and control culture influence sustainable performance by triggering innovation capabilities and investigate the moderating role of leadership style (i.e., transformational and transactional). The 186 matched questionnaire data from managers and employees in Chinese SMEs reveal that the flexibility and control culture are positively and negatively related to innovation capability, respectively, and that the latter mediates their influence on sustainable performance. Moreover, transformational leadership positively (negatively) moderates the relationship between flexibility (control) culture and innovation capability, while transactional leadership positively moderates the relationship between control culture and innovation capability. This study enriches the theoretical literature on corporate sustainable performance and provides management insights into how SMEs could survive and achieve sustained growth through corporate culture.

Safety and protective capability of an inactivated SARS-CoV-2 vaccine on pregnancy, lactation and the growth of offspring in hACE2 mice.

The mass inoculation of a severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) vaccine to induce herd immunity is one of the most effective measures to fight COVID-19. The vaccination of pregnant women cannot only avoid or reduce the probability of infectious diseases, but also offers the most effective and direct protection for neonates by means of passive immunization. However, there is no randomized clinical data to ascertain whether the inactivated vaccination of pregnant women or women of childbearing age can affect conception and the fetus. We found that human angiotensin-converting enzyme 2 (hACE2) mice that were vaccinated with two doses of CoronaVac (an inactivated SARS-CoV-2 vaccine) before and during pregnancy exhibited normal weight changes and reproductive performance indices; the physical development of their offspring was also normal. Following intranasal inoculation with SARS-CoV-2, pregnant mice in the immunization group all survived; reproductive performance indices and the physical development of offspring were all normal. In contrast, mice in the non-immunization group all died before delivery. Analyses showed that inoculation of CoronaVac was safe and did not exert any significant effects on pregnancy, lactation, or the growth of offspring in hACE2 mice. Vaccination effectively protected the pregnant mice against SARS-CoV-2 infection and had no adverse effects on the growth and development of the offspring, thus suggesting that inoculation with an inactivated SARS-CoV-2 vaccine may be an effective strategy to prevent infection in pregnant women.

Individual Preferences for COVID-19 Vaccination under the China's 2021 National Vaccination Policy: A Discrete Choice Experiment Study.

(1) Background: Since China's national vaccination policy announcement in January 2021, individual vaccination preferences related to vaccine characteristics, social relationships, sociodemographic characteristics and cognition remain opaque. This study aims to investigate vaccination preferences regarding these attributes, and to assess changes in individual vaccine preferences since the pre-2021 emergency vaccination phase. (2) Methods: The two-part questionnaire surveyed 849 individuals between May and June 2021 in Qingdao, China. The survey contained eight binary choice tasks that investigated preference trade-offs. Respondents' sociodemographic characteristics, including age, sex, urban/rural residence, income, education and whether living with the young or old, were also collected. Conditional logit, mixed logit and latent class models were used to quantify preference utility and identify preference heterogeneity. (3) Results: Vaccine effectiveness, vaccine side effects, duration of protection and probability of infection all significantly affected vaccination utility. Preference heterogeneity based on individual social relationships and sociodemographic characteristics were also established. Marginal analysis showed that compared to the pre-2021 phase, individuals' preferences had shifted towards vaccines with longer protection periods and better accessibility. (4) Conclusion: This study will inform the full rollout of China's 2021 national vaccination program and provide valuable information for future vaccination policy design to meet resurgent COVID-19 risks.

A matter of perspective-Cutting-edge technology-driven urine proteome in COVID-19.

In a recent issue of Nature Communications, we highlighted in-depth urine proteomic research in which significant immunosuppression was revealed in early SARS-CoV-2- infected patients 1. The application of urine in mapping the landscape of molecular changes closely associated with human diseases has been widely accepted. Herein, we take a systematic review of the published article from the perspective of both methodology and clinical significance.

Development and validation of an online model to predict critical COVID-19 with immune-inflammatory parameters.

BACKGROUND: Immune and inflammatory dysfunction was reported to underpin critical COVID-19(coronavirus disease 2019). We aim to develop a machine learning model that enables accurate prediction of critical COVID-19 using immune-inflammatory features at admission. METHODS: We retrospectively collected 2076 consecutive COVID-19 patients with definite outcomes (discharge or death) between January 27, 2020 and March 30, 2020 from two hospitals in China. Critical illness was defined as admission to intensive care unit, receiving invasive ventilation, or death. Least Absolute Shrinkage and Selection Operator (LASSO) was applied for feature selection. Five machine learning algorithms, including Logistic Regression (LR), Support Vector Machine (SVM), Gradient Boosted Decision Tree (GBDT), K-Nearest Neighbor (KNN), and Neural Network (NN) were built in a training dataset, and assessed in an internal validation dataset and an external validation dataset. RESULTS: Six features (procalcitonin, [T + B + NK cell] count, interleukin 6, C reactive protein, interleukin 2 receptor, T-helper lymphocyte/T-suppressor lymphocyte) were finally used for model development. Five models displayed varying but all promising predictive performance. Notably, the ensemble model, SPMCIIP (severity prediction model for COVID-19 by immune-inflammatory parameters), derived from three contributive algorithms (SVM, GBDT, and NN) achieved the best performance with an area under the curve (AUC) of 0.991 (95% confidence interval [CI] 0.979-1.000) in internal validation cohort and 0.999 (95% CI 0.998-1.000) in external validation cohort to identify patients with critical COVID-19. SPMCIIP could accurately and expeditiously predict the occurrence of critical COVID-19 approximately 20 days in advance. CONCLUSIONS: The developed online prediction model SPMCIIP is hopeful to facilitate intensive monitoring and early intervention of high risk of critical illness in COVID-19 patients. TRIAL REGISTRATION: This study was retrospectively registered in the Chinese Clinical Trial Registry ( ChiCTR2000032161 ). vv.

Individual preferences for COVID-19 vaccination in China.

BACKGROUND: Vaccinations are an effective choice to stop disease outbreaks, including COVID-19. There is little research on individuals' COVID-19 vaccination decision-making. OBJECTIVE: We aimed to determine individual preferences for COVID-19 vaccinations in China, and to assess the factors influencing vaccination decision-making to facilitate vaccination coverage. METHODS: A D-efficient discrete choice experiment was conducted across six Chinese provinces selected by the stratified random sampling method. Vaccine choice sets were constructed using seven attributes: vaccine effectiveness, side-effects, accessibility, number of doses, vaccination sites, duration of vaccine protection, and proportion of acquaintances vaccinated. Conditional logit and latent class models were used to identify preferences. RESULTS: Although all seven attributes were proved to significantly influence respondents' vaccination decision, vaccine effectiveness, side-effects and proportion of acquaintances vaccinated were the most important. We also found a higher probability of vaccinating when the vaccine was more effective; risks of serious side effects were small; vaccinations were free and voluntary; the fewer the number of doses; the longer the protection duration; and the higher the proportion of acquaintances vaccinated. Higher local vaccine coverage created altruistic herd incentives to vaccinate rather than free-rider problems. The predicted vaccination uptake of the optimal vaccination scenario in our study was 84.77%. Preference heterogeneity was substantial. Individuals who were older, had a lower education level, lower income, higher trust in the vaccine and higher perceived risk of infection, displayed a higher probability to vaccinate. CONCLUSIONS: Preference heterogeneity among individuals should lead health authorities to address the diversity of expectations about COVID-19 vaccinations. To maximize COVID-19 vaccine uptake, health authorities should promote vaccine effectiveness; pro-actively communicate the absence or presence of vaccine side effects; and ensure rapid and wide media communication about local vaccine coverage.

Immune suppression in the early stage of COVID-19 disease.

The outbreak of COVID-19 has become a worldwide pandemic. The pathogenesis of this infectious disease and how it differs from other drivers of pneumonia is unclear. Here we analyze urine samples from COVID-19 infection cases, healthy donors and non-COVID-19 pneumonia cases using quantitative proteomics. The molecular changes suggest that immunosuppression and tight junction impairment occur in the early stage of COVID-19 infection. Further subgrouping of COVID-19 patients into moderate and severe types shows that an activated immune response emerges in severely affected patients. We propose a two-stage mechanism of pathogenesis for this unusual viral infection. Our data advance our understanding of the clinical features of COVID-19 infections and provide a resource for future mechanistic and therapeutics studies.

Machine learning based early warning system enables accurate mortality risk prediction for COVID-19.

Soaring cases of coronavirus disease (COVID-19) are pummeling the global health system. Overwhelmed health facilities have endeavored to mitigate the pandemic, but mortality of COVID-19 continues to increase. Here, we present a mortality risk prediction model for COVID-19 (MRPMC) that uses patients' clinical data on admission to stratify patients by mortality risk, which enables prediction of physiological deterioration and death up to 20 days in advance. This ensemble model is built using four machine learning methods including Logistic Regression, Support Vector Machine, Gradient Boosted Decision Tree, and Neural Network. We validate MRPMC in an internal validation cohort and two external validation cohorts, where it achieves an AUC of 0.9621 (95% CI: 0.9464-0.9778), 0.9760 (0.9613-0.9906), and 0.9246 (0.8763-0.9729), respectively. This model enables expeditious and accurate mortality risk stratification of patients with COVID-19, and potentially facilitates more responsive health systems that are conducive to high risk COVID-19 patients.

Risk factors for developing into critical COVID-19 patients in Wuhan, China: A multicenter, retrospective, cohort study.

BACKGROUND: The ferocious global assault of COVID-19 continues. Critically ill patients witnessed significantly higher mortality than severe and moderate ones. Herein, we aim to comprehensively delineate clinical features of COVID-19 and explore risk factors of developing critical disease. METHODS: This is a Mini-national multicenter, retrospective, cohort study involving 2,387 consecutive COVID-19 inpatients that underwent discharge or death between January 27 and March 21, 2020. After quality control, 2,044 COVID-19 inpatients were enrolled. Electronic medical records were collected to identify the risk factors of developing critical COVID-19. FINDINGS: The severity of COVID-19 climbed up straightly with age. Critical group was characterized by higher proportion of dyspnea, systemic organ damage, and long-lasting inflammatory storm. All-cause mortality of critical group was 85•45%, by contrast with 0•58% for severe group and 0•18% for moderate group. Logistic regression revealed that sex was an effect modifier for hypertension and coronary heart disease (CHD), where hypertension and CHD were risk factors solely in males. Multivariable regression showed increasing odds of critical illness associated with hypertension, CHD, tumor, and age ≥ 60 years for male, and chronic obstructive pulmonary disease (COPD), chronic kidney disease (CKD), tumor, and age ≥ 60 years for female. INTERPRETATION: We provide comprehensive front-line information about different severity of COVID-19 and insights into different risk factors associated with critical COVID-19 between sexes. These results highlight the significance of dividing risk factors between sexes in clinical and epidemiologic works of COVID-19, and perhaps other coronavirus appearing in future. FUNDING: 10.13039/100000001 National Science Foundation of China.