RESUMEN
Background: Although current studies have identified sleep disorders as an independent risk factor for suicide, the relationship between sleep disorders and suicide risk has not been well established. This study explored whether anxiety and depressive symptoms are used as mediators to participate in the impact of sleep quality on suicide risk. Methods: This is a cross-sectional study. We administered a psychological questionnaire to the participants, using a combination of self-assessment and psychiatrist assessment.Sleep quality, suicide risk, level of anxiety and depressive symptoms were assessed by PSQI, NGASR, SAS and SDS.The study subjects were 391 hospitalized COVID-19 patients from Wuhan hospitals. We used model 6 in the PROCESS (version 3.5) plug-in of SPSS software to conduct mediation test with sleep quality as the independent variable, suicide risk as the dependent variable, level of anxiety and depressive symptoms as intermediate variables. Results: The severity of anxiety and depressive symptoms and the risk of suicide in the sleep disorder group (63.15 ± 13.71, 59.85 ± 13.38, 6.52 ± 3.67) were higher than those in the non-sleep disorder group (49.83 ± 13.14, 44.87 ± 10.19, 2.87 ± 3.26) (P < 0.001). The mediation model works well, The total indirect effect was 0.22 (95%CI = [0.17, 0.28]), and the direct effect was 0.16 (95%CI = [0.08, 0.24]). Limitations: This study used a self-assessment scale. Conclusions: Anxiety and depressive symptoms played a chain mediating role between sleep quality and suicide risk.
RESUMEN
Rapid worldwide spread of Coronavirus Disease 2019 (COVID 19) has resulted in a global pandemic. Correct facemask wearing is valuable in infectious disease control, but the effectiveness of facemasks has been diminished mostly due to improper wearing. However, there have not been any published reports on the automatic identification of facemask wearing conditions. In this study, we developed a new facemask wearing condition identification method in combination with image super resolution with classification network (SRCNet) SRCNet), which quantified a three categories classification problem based on unconstrained 2D facial image images. The proposed algorithm contained four main steps: image pre processing, face detection and crop, image super resolution, and face mask wearing conditions identification. Our method was trained and evaluated on public dataset Medical Masks Dataset containing 3835 images with 671 images of no facemask wearing, 134 images of incorrect facemask wearing, and 3030 images of correct facemask wearing. Finally, the proposed SRCNet achieved 98.70% accuracy and outperformed traditional end to end image classification methods using deep learning without image super resolution by over 1.5 in kappa. Our findings indicate that the proposed SRCNet could achieve high accuracy identification in facemask wearing conditions , which have potential application in epidemic prevention involving COVID 19.