ABSTRACT
Sleep staging has always been a hot topic in the field of sleep medicine, and it is the cornerstone of research on sleep problems. At present, sleep staging heavily relies on manual interpretation, which is a time-consuming and laborious task with subjective interpretation factors. In this paper, we propose an automatic sleep stage classification model based on the Bidirectional Recurrent Neural Network (BiRNN) with data bundling augmentation and label redirection for accurate sleep staging. Through extensive analysis, we discovered that the incorrect classification labels are primarily concentrated in the transition and nonrapid eye movement stage I (N1). Therefore, our model utilizes a sliding window input to enhance data bundling and an attention mechanism to improve feature enhancement after label redirection. This approach focuses on mining latent features during the N1 and transition periods, which can further improve the network model's classification performance. We evaluated on multiple public datasets and achieved an overall accuracy rate of 87.3%, with the highest accuracy rate reaching 93.5%. Additionally, the network model's macro F1 score reached 82.5%. Finally, we used the optimal network model to study the impact of different EEG channels on the accuracy of each sleep stage.
ABSTRACT
Objective: This study investigated the COVID-19-prevention knowledge and practices of healthcare workers (HCWs), their psychological states concerning the return to work, and their trust and requirements in using traditional Chinese medicine (TCM) to prevent and treat COVID-19. It is hoped that the study can serve as a reference for policy making during the resumption of work in other countries or regions experiencing similar situations. Methods: This study comprised a quantitative cross-sectional online survey design. Purposive sampling and Cluster sampling were used to recruit all HCWs working in public hospitals in Huangzhou District, Huanggang City, Hubei Province, China. From April 23 to May 14, 2020, surveys were sent electronically to all 13 public hospitals in this area. Results: In total, 2,079 responses were received and 2,050 completed forms were included. After analysis, 47.9 and 46.6% of HCWs indicated that they possessed very good knowledge or good knowledge of preventative measures, respectively. Multivariable log-binomial regression indicated that male, tertiary hospital, medical staff, and undergraduate/postgraduate qualification were associated with good knowledge. Good knowledge was also well-correlated with good practice (OR: 3.277; 95% CI: 2.734-3.928; P < 0.01). 59.8% of HCWs reported worries about resuming work; especially asymptomatic infections. The Self-Rating Anxiety Scale (SAS) indicated that 10.8% of participants had mild anxiety, 1.5% moderate anxiety, and 0.1% severe anxiety. Female, divorced/widowed, and working in a high risk hospital (the Huangzhou District People's Hospital was used for throat swab examinations of returning workers) were risk factors for concerns about resuming work and anxiety symptoms. However, good preventive knowledge was a protective factor for anxiety. HCWs' trust in using TCM to treat COVID-19 was significantly higher than their trust in using TCM for prevention (P < 0.001). Regarding preferences for preventative TCM products, oral TCM granules were the most preferred (62.4%). HCWs also indicated they wanted to know more about the clinical efficacy, applicable population, and adverse reactions of preventative TCM products (89.3, 81.1, and 81.4%, respectively). Conclusion: While HCWs had good knowledge of COVID-19 preventative measures, this did not eliminate the psychological impact of resumption of work. Promotion of COVID-19 prevention knowledge reduces the risk of infection, and alleviates the worries and anxiety symptoms of HCWs about resuming work (especially in administrative staff, those with low education, and those working in primary hospitals). Additional psychological support is required for female HCWs, divorced/widowed HCWs, and those working in high-risk hospitals. Finally, systematic trials of preventative TCM products are recommended.
Subject(s)
COVID-19 , Return to Work , China , Cross-Sectional Studies , Female , Health Personnel , Humans , Male , SARS-CoV-2ABSTRACT
Objective: The objective of this study was to investigate how knowledge and practice of coronavirus disease 2019 (COVID-19) prevention measures affected concerns about returning to work among supermarket staff. Attitudes about the ability of traditional Chinese medicine (TCM) to prevent COVID-19 were also assessed. Methods: A cross-sectional study was conducted in Huanggang, Hubei Province, China from April 23 to 25, 2020. Participants were invited to fill out an electronic questionnaire on their cell phones. Results: The results showed that from 2,309 valid questionnaires, 61.5% of participants were concerned about resuming work. Major concerns included asymptomatic infection (85.01%) and employees gathering in the workplace (78.96%). Multivariate logistic regression indicated that the female gender, having school-aged children and pregnancy were risk factors for being concerned about resuming work, while good knowledge and practice of preventive measures were protective factors. Knowledge and practice of preventive measures were positively correlated. Among preventive measures, the highest percentage of participants knew about wearing masks and washing hands. Meanwhile, 65.8% of participants expressed confidence in the ability of TCM to prevent COVID-19, where 74 and 51.3% thought there was a need and a strong need, respectively, for preventive TCM-based products. Among them, 71.5% preferred oral granules. Regarding TCM as a COVID-19 preventative, most were interested in information about safety and efficacy. Conclusion: These findings suggested that promoting knowledge and practices regarding COVID-19 prevention can help alleviate concerns about returning to work. Meanwhile, TCM can feasibly be accepted to diversify COVID-19 prevention methods. Clinical Trial Registration:http://www.chictr.org.cn/, identifier: ChiCTR2000031955.