A systematic hybrid machine learning approach for stress prediction.

Stress is becoming an increasingly prevalent health issue, seriously affecting people and putting their health and lives at risk. Frustration, nervousness, and anxiety are the symptoms of stress and these symptoms are becoming common (40%) in younger people. It creates a negative impact on human lives and damages the performance of each individual. Early prediction of stress and the level of stress can help to reduce its impact and different serious health issues related to this mental state. For this, automated systems are required so they can accurately predict stress levels. This study proposed an approach that can detect stress accurately and efficiently using machine learning techniques. We proposed a hybrid model (HB) which is a combination of gradient boosting machine (GBM) and random forest (RF). These models are combined using soft voting criteria in which each model's prediction probability will be used for the final prediction. The proposed model is significant with 100% accuracy in comparison with the state-of-the-art approaches. To show the significance of the proposed approach we have also done 10-fold cross-validation using the proposed model and the proposed HB model outperforms with 1.00 mean accuracy and +/-0.00 standard deviation. In the end, a statistical T-test we have done to show the significance of the proposed approach in comparison with other approaches.

College students' anxiety after returning to school during the COVID-19 epidemic: What should we care.

The college students' anxiety during the Coronavirus disease 2019 (COVID-19) epidemic remains unclear. We aimed to evaluate the college students' anxiety after returning to school during the COVID-19 epidemic, to provide reference for the management and nursing care of college students. We conducted a survey from September 15, 2021 to September 30, 2021 investigate the anxiety level of college students. The Self-rating Anxiety Scale was used for anxiety assessment. The Spearman correlation analysis was conducted to evaluate the correlation between students' anxiety and characteristics. Logistic regression analysis was used to explore the influencing factors of concurrent anxiety among college students. A total of 2168 college students were included, the incidence of anxiety was 30.07% in college students during the COVID-19 epidemic. Pearson correlation analyses showed that grade (R = 0.715), main use of computer and mobile phone (R = 0.622), daily exercise (R = 0.735), whether relatives or friends are infected with COVID-19 (R = 0.735) are associated with the anxiety level of college students (all P < .05). Logistic regression analysis indicated that senior year (Odds ratio [OR] = 2.064, 95% confidence interval [CI]: 1.355-3.001), online game (OR = 3.122, 95% CI: 2.562-3.899), relatives or friends are infected with COVID-19 (OR = 2.987, 95% CI: 1.901-3.451) are the independent risk factors of anxiety in college students (all P < .05). Daily exercise (OR = 0.514, 95% CI: 0.205-0.814) was the independent protective factors of anxiety in college students (P = .008). During the COVID-19 epidemic, college students have increased anxiety and there are many influencing factors. Administrators and educators should especially pay attention to the mental health of students with those risk factors to maintain students' physical and mental health.

Mechanism of selenomethionine inhibiting of PDCoV replication in LLC-PK1 cells based on STAT3/miR-125b-5p-1/HK2 signaling.

There are no licensed therapeutics or vaccines available against porcine delta coronavirus (PDCoV) to eliminate its potential for congenital disease. In the absence of effective treatments, it has led to significant economic losses in the swine industry worldwide. Similar to the current coronavirus disease 2019 (COVID-19) pandemic, PDCoV is trans-species transmissible and there is still a large desert for scientific exploration. We have reported that selenomethionine (SeMet) has potent antiviral activity against PDCoV. Here, we systematically investigated the endogenous immune mechanism of SeMet and found that STAT3/miR-125b-5p-1/HK2 signalling is essential for the exertion of SeMet anti-PDCoV replication function. Meanwhile, HK2, a key rate-limiting enzyme of the glycolytic pathway, was able to control PDCoV replication in LLC-PK1 cells, suggesting a strategy for viruses to evade innate immunity using glucose metabolism pathways. Overall, based on the ability of selenomethionine to control PDCoV infection and transmission, we provide a molecular basis for the development of new therapeutic approaches.

Targeted delivery of inhalable drug particles in a patient-specific tracheobronchial tree with moderate COVID-19: A numerical study.

The coronavirus disease 2019 (COVID-19) pandemic has led to severe social and economic disruption worldwide. Although currently no consent has been reached on a specific therapy that can treat COVID-19 effectively, several inhalation therapy strategies have been proposed to inhibit SARS-CoV-2 infection. These strategies include inhalations of antiviral drugs, anti-inflammatory drugs, and vaccines. To investigate how to enhance the therapeutic effect by increasing the delivery efficiency (DE) of the inhaled aerosolized drug particles, a patient-specific tracheobronchial (TB) tree from the trachea up to generation 6 (G6) with moderate COVID-19 symptoms was selected as a testbed for the in silico trials of targeted drug delivery to the lung regions with pneumonia alba, i.e., the severely affected lung segments (SALS). The 3D TB tree geometry was reconstructed from spiral computed tomography (CT) scanned images. The airflow field and particle trajectories were solved using a computational fluid dynamics (CFD) based Euler-Lagrange model at an inhalation flow rate of 15 L/min. Particle release maps, which record the deposition locations of the released particles, were obtained at the inlet according to the particle trajectories. Simulation results show that particles with different diameters have similar release maps for targeted delivery to SALS. Point-source aerosol release (PSAR) method can significantly enhance the DE into the SALS. A C++ program has been developed to optimize the location of the PSAR tube. The optimized simulations indicate that the PSAR approach can at least increase the DE of the SALS by a factor of 3.2× higher than conventional random-release drug-aerosol inhalation. The presence of the PSAR tube only leads to a 7.12% change in DE of the SALS. This enables the fast design of a patient-specific treatment for reginal lung diseases.

The Triangle Relationship Between Long Noncoding RNA, RIG-I-like Receptor Signaling Pathway, and Glycolysis.

Long noncoding RNA (LncRNA), a noncoding RNA over 200nt in length, can regulate glycolysis through metabolic pathways, glucose metabolizing enzymes, and epigenetic reprogramming. Upon viral infection, increased aerobic glycolysis providzes material and energy for viral replication. Mitochondrial antiviral signaling protein (MAVS) is the only protein-specified downstream of retinoic acid-inducible gene I (RIG-I) that bridges the gap between antiviral immunity and glycolysis. MAVS binding to RIG-I inhibits MAVS binding to Hexokinase (HK2), thereby impairing glycolysis, while excess lactate production inhibits MAVS and the downstream antiviral immune response, facilitating viral replication. LncRNAs can also regulate antiviral innate immunity by interacting with RIG-I and downstream signaling pathways and by regulating the expression of interferons and interferon-stimulated genes (ISGs). Altogether, we summarize the relationship between glycolysis, antiviral immunity, and lncRNAs and propose that lncRNAs interact with glycolysis and antiviral pathways, providing a new perspective for the future treatment against virus infection, including SARS-CoV-2.

Newly-Diagnosed Diabetes and Sustained Hyperglycemia are Associated with Poorer Outcomes in COVID-19 Inpatients Without Pre-Existing Diabetes.

PURPOSE: To analyze the impact of hyperglycemia on the clinical outcome of COVID-19 in patients with newly diagnosed diabetes (NDD). PATIENTS AND METHODS: We performed a retrospective study of 3114 cases of COVID-19 without pre-existing diabetes, 351 of which had NDD, in Hubei Province, China. The Cox regression model was used to calculate the risk of adverse clinical outcomes comparing the NDD vs non-NDD group before and after propensity score-matched (PSM) analysis. Patients with NDD were further divided into a sustained hyperglycemia group, a fluctuating group, and a remitted group based on their blood glucose levels during hospitalization as well as into hypoglycemic agent users and nonusers. RESULTS: Compared to the non-NDD individuals, individuals with NDD had a significantly increased risk of all-cause mortality (adjusted HR after PSM, 2.65; 95% CI, 1.49-4.72; P = 0.001) and secondary outcomes involving organ damage during the 28-day follow-up period. Subgroup analyses indicated that among individuals with NDD, the individuals with remitted hyperglycemia had the lowest 28-day mortality, whereas those with sustained hyperglycemia had the highest (IRR 24.27; 95% CI, 3.21-183.36; P < 0.001). Moreover, individuals treated with hypoglycemic agents had significantly lower all-cause mortality than those not treated with hypoglycemic agents (IRR 0.08; 95% CI, 0.01-0.56; P < 0.001). CONCLUSION: Our study reinforces the clinical message that NDD is strongly associated with poor outcomes in COVID-19 patients. Furthermore, resolved hyperglycemia in the later phase of the disease and the use of hypoglycemic agents were associated with improved prognosis in patients with NDD.

Potential Influence of Menstrual Status and Sex Hormones on Female Severe Acute Respiratory Syndrome Coronavirus 2 Infection: A Cross-sectional Multicenter Study in Wuhan, China.

BACKGROUND: Recent studies have indicated that females with coronavirus disease 2019 (COVID-19) have a lower morbidity, severe case rate, and mortality and better outcome than those of male individuals. However, the reasons remained to be addressed. METHODS: To find the factors that potentially protect females from COVID-19, we recruited all confirmed patients hospitalized at 3 branches of Tongji Hospital (N = 1902), and analyzed the correlation between menstrual status (n = 509, including 68 from Mobile Cabin Hospital), female hormones (n = 78), and cytokines related to immunity and inflammation (n = 263), and the severity/clinical outcomes in female patients <60 years of age. RESULTS: Nonmenopausal female patients had milder severity and better outcome compared with age-matched men (P < .01 for both). Menopausal patients had longer hospitalization times than nonmenopausal patients (hazard ratio [HR], 1.91 [95% confidence interval {CI}, 1.06-3.46]; P = .033). Both anti-Müllerian hormone (AMH) and estradiol (E2) showed a negative correlation with severity of infection (adjusted HR, 0.146 [95% CI, .026-.824], P = .029 and 0.304 [95% CI, .092-1.001], P = .05, respectively). E2 levels were negatively correlated with interleukin (IL) 2R, IL-6, IL-8, and tumor necrosis factor alpha in the luteal phase (P = .033, P = .048, P = .054, and P = .023) and C3 in the follicular phase (P = .030). CONCLUSIONS: Menopause is an independent risk factor for female COVID-19 patients. AMH and E2 are potential protective factors, negatively correlated with COVID-19 severity, among which E2 is attributed to its regulation of cytokines related to immunity and inflammation.

Analysis of Ovarian Injury Associated With COVID-19 Disease in Reproductive-Aged Women in Wuhan, China: An Observational Study.

Objective: This study was intended to investigate the relationship between COVID-19 disease and ovarian function in reproductive-aged women. Methods: Female COVID-19 patients of reproductive age were recruited between January 28 and March 8, 2020 from Tongji Hospital in Wuhan. Their baseline and clinical characteristics, as well as menstrual conditions, were recorded. Differentials in ovarian reserve markers and sex hormones (including anti-Müllerian hormone [AMH], follicle-stimulating hormone [FSH], the ratio of FSH to luteinizing hormone [LH], estradiol [E2], progesterone [P], testosterone [T], and prolactin [PRL] were compared to those of healthy women who were randomly selected and individually matched for age, region, and menstrual status. Uni- and multi-variable hierarchical linear regression analyses were performed to identify risk factors associated with ovarian function in COVID-19 women. Results: Seventy eight patients agreed to be tested for serum hormone, of whom 17 (21.79%) were diagnosed as the severe group and 39 (50%) were in the basal level group. Menstrual status (P = 0.55), menstrual volumes (P = 0.066), phase of menstrual cycle (P = 0.58), and dysmenorrhea history (P = 0.12) were similar without significant differences between non-severe and severe COVID-19 women. Significant lower serum AMH level/proportion (0.19/0.28 vs. 1.12 ng/ml, P = 0.003/0.027; AMH ≤ 1.1 ng/ml: 75/70.4 vs. 49.7%, P = 0.009/0.004), higher serum T (0.38/0.39 vs. 0.22 ng/ml, P < 0.001/0.001) and PRL (25.43/24.10 vs. 12.12 ng/ml, P < 0.001/0.001) levels were observed in basal level and the all-COVID-19 group compared with healthy age-matched control. When adjusted for age, menstrual status and parity variations in multivariate hierarchical linear regression analysis, COVID-19 disease was significantly associated with serum AMH (ß = -0.191; 95% CI: -1.177-0.327; P = 0.001), T (ß = 0.411; 95% CI: 11.154-22.709; P < 0.001), and PRL (ß = 0.497; 95% CI: 10.787-20.266; P < 0.001), suggesting an independent risk factor for ovarian function, which accounted for 3.2% of the decline in AMH, 14.3% of the increase in T, and 20.7% of the increase in PRL. Conclusion: Ovarian injury, including declined ovarian reserve and reproductive endocrine disorder, can be observed in women with COVID-19. More attention should be paid to their ovarian function under this pandemic, especially regarding reproductive-aged women. Clinical Trial Number: ChiCTR2000030015.