Depression screening using hybrid neural network

Depression is a common cause of increased suicides worldwide, and studies have shown that the number of patients suffering from major depressive disorder (MDD) increased several-fold during the COVID-19 pandemic, highlighting the importance of disease detection and depression management, while increasing the need for effective diagnostic tools. In recent years, machine learning and deep learning methods based on electroencephalography (EEG) have achieved significant results in the field of automatic depression detection. However, most current studies have focused on a small number of EEG signal channels, and experimental data require special processing by professionals. In this study, 128 channels of EEG signals were simply filtered and 24-fold leave-one-out cross-validation experiments were performed using 2DCNN-LSTM classifier, support vector machine, K-nearest neighbor and decision tree. The current results show that the proposed 2DCNN-LSTM model has an average classification accuracy of 95.1% with an AUC of 0.98 for depression detection of 6-second participant EEG signals, and the model is much better than 72.05%, 79.7% and 79.49% for support vector machine, K nearest neighbor and decision tree. In addition, we found that the model achieved a 100% probability of correctly classifying the EEG signals of 300-second participants.

Online-Based Survey on College Students' Anxiety During COVID-19 Outbreak.

PURPOSE: Studies have suggested that public health emergencies can have many psychological effects on college students, therefore, the aim of this study is to investigate current situation of college students' anxiety and its determinants in the time of an unexpected pandemic. PATIENTS AND METHODS: We conducted convenience sampling to collect the data through network-based online questionnaires in February 2020, a total of 17,876 college students were included in the analysis. Chi-square test and multivariate logistic were used to identify the associations between the outbreak experiences and anxiety detection. RESULTS: This study found that detection rate of anxiety among college students was 18.2%. The differences in male students, students whose self-perceived risk of infection were high, who were greatly affected by the outbreak, eager to go back to school, reluctant to leave home and stay at home enough were of statistical significance among different anxiety level (OR>1, P<0.05). And the severe anxiety rate of students who living in cities was significantly higher (2.337[1.468, 3.721]). CONCLUSION: Although our results show that anxiety among college students was at a low level, various universities should focus on the online activities and develop appropriate epidemic management plans to prevent their feelings of worry, tension and panic.

Depression screening using hybrid neural network.

Depression is a common cause of increased suicides worldwide, and studies have shown that the number of patients suffering from major depressive disorder (MDD) increased several-fold during the COVID-19 pandemic, highlighting the importance of disease detection and depression management, while increasing the need for effective diagnostic tools. In recent years, machine learning and deep learning methods based on electroencephalography (EEG) have achieved significant results in the field of automatic depression detection. However, most current studies have focused on a small number of EEG signal channels, and experimental data require special processing by professionals. In this study, 128 channels of EEG signals were simply filtered and 24-fold leave-one-out cross-validation experiments were performed using 2DCNN-LSTM classifier, support vector machine, K-nearest neighbor and decision tree. The current results show that the proposed 2DCNN-LSTM model has an average classification accuracy of 95.1% with an AUC of 0.98 for depression detection of 6-second participant EEG signals, and the model is much better than 72.05%, 79.7% and 79.49% for support vector machine, K nearest neighbor and decision tree. In addition, we found that the model achieved a 100% probability of correctly classifying the EEG signals of 300-second participants.

Association between Family Support, Stress, and Sleep Quality among College Students during the COVID-19 Online Learning Period.

(1) Background: During the past 3 years, the COVID-19 pandemic has severely affected the normal school schedule of college students, jeopardizing their mental health, sleep quality, and interpersonal relationships. However, previous studies have focused on the dimension of social support received, and few studies have measured in depth the association of support received from family on adolescents' physical and mental health. Therefore, this study explored the associations between family support received by Chinese college students during COVID-19 pandemic online classes, stress and sleep quality, and the mediating role of stress. (2) Methods: A cross-sectional study conducted at Chongqing Medical University recruited 712 college students through a university-wide incidental random sample using the Questionnaire Star platform. Statistical description and correlation analysis was conducted using SPSS 25.0, and structural equation modeling was constructed using AMOS 22.0 to test for mediating effects; (3) Results: The family support score of college students during the COVID-19 pandemic online course was 19.41 ± 4.62. Correlation analysis showed that sleep quality was negatively correlated with family support (r = −0.224, p < 0.01), positively correlated with stress (r = 0.324, p < 0.01), and family support was negatively correlated with stress (r = −0.159, p < 0.01). The results of structural equation modeling showed that stress partially mediated the relationship between family support and sleep quality among college students (indirect effect = −0.150, p < 0.01, SE = 0.013,95% CI = [−0.208, −0.064]). The model R2 was 36.4%. (4) Conclusions: Schools should consider implementing sleep education, and stress relief curriculum measures to improve the quality of students' sleep, and should focus on the role that family plays during online classes. This will help students overcome the negative emotional effects of stress in the COVID-19 pandemic and improve their learning efficiency and physical and mental health.

Pemphigus during the COVID-19 Epidemic: Infection Risk, Vaccine Responses and Management Strategies.

Pemphigus is a rare autoimmune blistering disease, involving potentially life-threatening conditions often requiring immunosuppression. Currently, the COVID-19 pandemic caused by severe acute respiratory disease coronavirus 2 (SARS-CoV-2) infection has become a global public emergency. Vaccines are the most effective defense against COVID-19 infection. However, in clinic, there are cases of new onset or flare of pemphigus following COVID-19 vaccination, where vaccines have manifested significantly desirable risk-benefit profiles for patients. Although Rituximab, as first-line therapy, may impair humoral immunity, pemphigus may not predispose to develop COVID-19 infection compared to a healthy population. Conversely, delay or interruption of immunosuppressants probably results in unfavorable clinical outcomes for disease progression. Overall, clinicians should encourage their patients to undergo the vaccination after a comprehensive assessment. The definite association between COVID-19 vaccination and pemphigus remains to be further elucidated. Herein, we provide an overview of the published studies to date on COVID-19 and pemphigus as well as the exploration of their complicated interplay. In addition, we discuss the management strategies for pemphigus patients in this special period, in an effort to more effectively establish a standard treatment paradigm for this particular patient group.

Small-Molecule Compound SYG-180-2-2 to Effectively Prevent the Biofilm Formation of Methicillin-Resistant Staphylococcus aureus.

The resistance of methicillin-resistant Staphylococcus aureus (MRSA) has augmented due to the abuse of antibiotics, bringing about difficulties in the treatment of infection especially with the formation of biofilm. Thus, it is essential to develop antimicrobials. Here we synthesized a novel small-molecule compound, which we termed SYG-180-2-2 (C21H16N2OSe), that had antibiofilm activity. The aim of this study was to demonstrate the antibiofilm effect of SYG-180-2-2 against clinical MRSA isolates at a subinhibitory concentration (4 µg/ml). In this study, it was showed that significant suppression in biofilm formation occurred with SYG-180-2-2 treatment, the inhibition ranged between 65.0 and 85.2%. Subsequently, confocal laser scanning microscopy and a bacterial biofilm metabolism activity assay further demonstrated that SYG-180-2-2 could suppress biofilm. Additionally, SYG-180-2-2 reduced bacterial adhesion and polysaccharide intercellular adhesin (PIA) production. It was found that the expression of icaA and other biofilm-related genes were downregulated as evaluated by RT-qPCR. At the same time, icaR and codY were upregulated when biofilms were treated with SYG-180-2-2. Based on the above results, we speculate that SYG-180-2-2 inhibits the formation of biofilm by affecting cell adhesion and the expression of genes related to PIA production. Above all, SYG-180-2-2 had no toxic effects on human normal alveolar epithelial cells BEAS-2B. Collectively, the small-molecule compound SYG-180-2-2 is a safe and effective antibacterial agent for inhibiting MRSA biofilm.

Nonlinear dynamic mechanism of regional air pollution during the COVID-19 lockdown

Based on hourly concentration of PM2.5 and O3 during the epidemic period（January 24, 2020 to May 31, 2020） in Changsha, Zhuzhou and Xiangtan, the diurnal patterns, long-term persistence, multifractality and self-organization evolution dynamics of these two pollutants were studied to reveal the internal dynamic mechanism of the occurrence and evolution of heavy pollution events during the epidemic period. Firstly, the diurnal patterns of PM2.5 and O3 concentrations were investigated. It showed that O3 showed a single peak of high concentration in the daytime and low in the night, while PM2.5 showed a single lowest peak concentration in the day and high in the night, which was different from the pattern in non-epidemic periods. Furthermore, detrended fluctuation analysis（DFA）, the multifractal detrended fluctuation analysis（MFDFA） and probability statistical analysis were applied to study the long-term persistence, multi-fractal structure of PM2.5 and O3 series. The results showed that PM2.5 and O3 series had significant long-term persistence characteristics and strong multi-fractal structures for the three cities. Meanwhile, detrended cross-correlation analysis（DCCA） and multifractal detrended cross-correlation analysis（MFDCCA） were conducted to estimate the cross-correlations between PM2.5 and O3 series. Long-term persistence as well as multifractal features at different time scales was also observed in PM2.5-O3 cross-correlations. Next, nonlinear analysis results obtained during epidemic period were compared with those obtained in the same periods of non-epidemic years of 2019 and 2018. Finally, based on the self-organized criticality（SOC） theory, the internal dynamic law of spatial and temporal evolution of PM2.5 and O3 series was discussed. Combined with the typical regional meteorological characteristics, it was found that the intrinsic dynamic mechanism of SOC may be one of the leading mechanisms of heavy air pollution episodes during the COVID-19 lockdown period. During the epidemic period, PM2.5 and O3 concentrations did not evolve independently but remained complex interactions. Under the stable meteorological conditions, the nonlinear coupling effect inside the air combined pollution might reach the dynamic critical state, thus, lead to the risk of heavy air pollution in Greater Changsha Metropolitan Region during the epidemic period.

Network-Based Online Survey Exploring Self-Reported Depression Among University and College Students During the Early Days of the COVID-19 Outbreak.

Background: The psychology of university and college students is immature, they are thus more likely to suffer from depression due to the COVID-19 pandemic. The present study aims to investigate the self-reported depression status of Chinese university and college students and explore its influencing factors. Methods: We conducted a network-based online survey, and a total of 17,876 participants completed the questionnaire. Depression was measured by the Self-Rating Depression Scale (SDS). Univariate analysis and multivariate logistic analysis were performed to explore the influencing factors of self-reported depression symptoms. Results: The proportion of self-reported depression symptoms, mild self-reported depression symptoms, and moderate to severe (M/S) self-reported depression symptoms was 65.2, 53.7, and 11.5%, respectively. The mean score of self-reported depression was 54.8 ± 9.0. Female, personality type of partial introversion, junior college educational level, "moderate" or "high" self-perceived risk of infection, "moderately" or "highly" impacted by the outbreak, and being eager to go back to school were risk factors for M/S self-reported depression symptoms (p < 0.05). While, "moderate" or "high" concern about the outbreak, "moderate" or "high" satisfaction with pandemic prevention and control measures, and having health literacy on communicable diseases were protective factors for M/S self-reported depression symptoms (p < 0.05). Conclusion: The status of self-reported depression symptoms among university and college students was severer than expected, and the influencing factors were multifaceted. Government and school administrators should strengthen the dissemination of knowledge on disease prevention and control. Moreover, much attention should be paid to female and junior college students.

Did anthropause generate a research pause during the pandemic? The experiences of a non-medical journal.

Contradicting expectations, a non-medical journal received increasing submissions during the pandemic, even though laboratories remained closed.Peer reviewers and handling editors were both more responsive and provided faster turnaround times during 2020.The reasons for increased submission to the journal may have been due to reanalysis of older data or extracting more findings from research done pre-pandemic.

Open resource of clinical data from patients with pneumonia for the prediction of COVID-19 outcomes via deep learning.

Data from patients with coronavirus disease 2019 (COVID-19) are essential for guiding clinical decision making, for furthering the understanding of this viral disease, and for diagnostic modelling. Here, we describe an open resource containing data from 1,521 patients with pneumonia (including COVID-19 pneumonia) consisting of chest computed tomography (CT) images, 130 clinical features (from a range of biochemical and cellular analyses of blood and urine samples) and laboratory-confirmed severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) clinical status. We show the utility of the database for prediction of COVID-19 morbidity and mortality outcomes using a deep learning algorithm trained with data from 1,170 patients and 19,685 manually labelled CT slices. In an independent validation cohort of 351 patients, the algorithm discriminated between negative, mild and severe cases with areas under the receiver operating characteristic curve of 0.944, 0.860 and 0.884, respectively. The open database may have further uses in the diagnosis and management of patients with COVID-19.

MDM2-Mediated Ubiquitination of Angiotensin-Converting Enzyme 2 Contributes to the Development of Pulmonary Arterial Hypertension.

BACKGROUND: Angiotensin-converting enzyme 2 (ACE2) converts angiotensin II, a potent vasoconstrictor, to angiotensin-(1-7) and is also a membrane protein that enables coronavirus disease 2019 (COVID-19) infectivity. AMP-activated protein kinase (AMPK) phosphorylation of ACE2 enhances ACE2 stability. This mode of posttranslational modification of ACE2 in vascular endothelial cells is causative of a pulmonary hypertension (PH)-protective phenotype. The oncoprotein MDM2 (murine double minute 2) is an E3 ligase that ubiquitinates its substrates to cause their degradation. In this study, we investigated whether MDM2 is involved in the posttranslational modification of ACE2 through its ubiquitination of ACE2, and whether an AMPK and MDM2 crosstalk regulates the pathogenesis of PH. METHODS: Bioinformatic analyses were used to explore E3 ligase that ubiquitinates ACE2. Cultured endothelial cells, mouse models, and specimens from patients with idiopathic pulmonary arterial hypertension were used to investigate the crosstalk between AMPK and MDM2 in regulating ACE2 phosphorylation and ubiquitination in the context of PH. RESULTS: Levels of MDM2 were increased and those of ACE2 decreased in lung tissues or pulmonary arterial endothelial cells from patients with idiopathic pulmonary arterial hypertension and rodent models of experimental PH. MDM2 inhibition by JNJ-165 reversed the SU5416/hypoxia-induced PH in C57BL/6 mice. ACE2-S680L mice (dephosphorylation at S680) showed PH susceptibility, and ectopic expression of ACE2-S680L/K788R (deubiquitination at K788) reduced experimental PH. Moreover, ACE2-K788R overexpression in mice with endothelial cell-specific AMPKα2 knockout mitigated PH. CONCLUSIONS: Maladapted posttranslational modification (phosphorylation and ubiquitination) of ACE2 at Ser-680 and Lys-788 is involved in the pathogenesis of pulmonary arterial hypertension and experimental PH. Thus, a combined intervention of AMPK and MDM2 in the pulmonary endothelium might be therapeutically effective in PH treatment.

Asymptomatic carriers of COVID-19 as a concern for disease prevention and control: more testing, more follow-up.

Following a containment phase of two months, China has transitioned to the mitigation phase. However, China still faces the risk of COVID-19 spreading due to not only to sporadic new cases and imported cases but also asymptomatic carriers. According to daily reports from the National Health Commission of the People's Republic of China from March 31, 2020 to April 7, 2020, the number of new asymptomatic cases reported daily greatly exceeded that of new imported cases. As of 24:00 on April 7, there were a total of 1,095 asymptomatic cases with COVID-19 under medical observation on the Chinese mainland, including 358 imported cases. A growing number of studies have indicated that asymptomatic carriers are infectious to an extent and can potentially transmit COVID-19. At present, China's measures for managing asymptomatic carriers are 14 days of centralized quarantine and observation; in principle, people with two consecutive negative nucleic acid tests (at an interval of at least 24 hours) can be released from quarantine. However, asymptomatic carriers will not be included in confirmed cases unless they develop clinical manifestations while in quarantine. As "silent spreaders", asymptomatic carriers warrant attention as part of disease prevention and control. The testing and follow-up of asymptomatic carriers should be expanded to include people in close contact with patients with confirmed COVID-19 and asymptomatic cases, clusters of outbreaks, and key areas and populations with a high risk of infection.