A Deep Ensemble Dynamic Learning Network for Corona Virus Disease 2019 Diagnosis.

Corona virus disease 2019 is an extremely fatal pandemic around the world. Intelligently recognizing X-ray chest radiography images for automatically identifying corona virus disease 2019 from other types of pneumonia and normal cases provides clinicians with tremendous conveniences in diagnosis process. In this article, a deep ensemble dynamic learning network is proposed. After a chain of image preprocessing steps and the division of image dataset, convolution blocks and the final average pooling layer are pretrained as a feature extractor. For classifying the extracted feature samples, two-stage bagging dynamic learning network is trained based on neural dynamic learning and bagging algorithms, which diagnoses the presence and types of pneumonia successively. Experimental results manifest that using the proposed deep ensemble dynamic learning network obtains 98.7179% diagnosis accuracy, which indicates more excellent diagnosis effect than existing state-of-the-art models on the open image dataset. Such accurate diagnosis effects provide convincing evidences for further detections and treatments.

Analysis of Healthcare Workers' Knowledge About Vital Sign Zero and Identify-Isolate-Inform (3I) System in the Diagnosis and Prevention of Infectious Diseases in Chinese Tertiary Hospitals.

Objective: To explore the current knowledge and application of vital sign zero and the identify-isolate-inform (3I) system among healthcare workers in China in order to provide a reference for future improvement of healthcare workers' awareness of personal protection and prevention and control measures of infectious diseases. Methods: The questionnaire was used to investigate the basic information of health care workers, their knowledge and application of Vital sign zero and the 3I system. A total of 602 forms of health care workers from tertiary hospitals were randomly collected and included for analysis. Results: The survey showed that 45.30% and 57.30% of the healthcare workers from Chinese tertiary hospitals know about vital sign zero and 3I system while 51.80% and 57.30% of them applied these measures in their clinical practices. Logistics regression analysis results showed that healthcare workers aged 35 years old and below were less aware of vital sign zero than those above 50 years old (OR = 0.405, 95% CI: 0.174-0.942, P = 0.036). Compared with those in Northwest China, healthcare workers who worked in East China (OR = 0.147, 95% CI: 0.031-0.702, P = 0.016), Central China (OR = 0.085, 95% CI: 0.018-0.403, P = 0.002), Southwest China (OR = 0.083, 95% CI: 0.014-0.48, P = 0.006) and North China (OR = 0.201, 95% CI: 0.042-0.966, P = 0.045) were less aware of vital sign zero while the healthcare workers in Northeast China (OR=9.714, 95% CI: 1.091-86.521, P = 0.042), East China (OR = 18.049, 95% CI: 2.258-144.259, P = 0.006), Central China (OR = 25.560, 95% CI: 3.210-203.502, P = 0.002), South China (OR = 11.141, 95% CI: 1.395-88.947, P = 0.023), Southwest China (OR = 23.200, 95% CI: 2.524-213.286, P = 0.005) and North China (OR = 14.078, 95% CI: 1.756-112.895, P = 0.013) had a better understanding of the 3I system than those in Northwest China. Healthcare workers with more than 20 years of working experience showed less knowledge of the 3I system than those with less than 5 years of working experience (OR = 0.409, 95% CI: 0.215-0.77, P = 0.006). Conclusion: The current levels of knowledge and application of vital sign zero and the 3I system in the healthcare workers of Chinese tertiary hospitals need to be improved. The concept of vital sign zero should be incorporated into the prevention triage system of infectious diseases.

Practices of poverty alleviation by open and distance education: a case report from the Open University of China

PurposeThe purpose of this report is to demonstrate open and distance education (ODE) can support poverty alleviation. Taking the practices of the Open University of China (the OUC) as an example, this paper aims to reveal how open universities make contributions to local residents in rural and remote areas.Design/methodology/approachFocusing on 25 poverty-stricken counties, the OUC had invested 58 million RMB to its learning centers in these counties from 2017 to 2020. The first one is to improve ICT and educational facilities in these learning centers. The second approach is to cultivate local residents with degree programs through ODE so as to promote local economic development. The third one is to design and develop training programs according to local context to meet the specific needs of local villagers.FindingsAfter 3 years working, cloud-based classrooms and computer rooms have been set up. Bookstores have been founded and printed books have been donated. Hundreds of thousands of digital micro lectures have been supplied to these learning centers which have been improved and fully played their functions. Nearly 50,000 local residents have been directly benefited. Village leaders have helped lift local residents out of poverty. Poverty-stricken villagers have been financed to study on either undergraduate or diploma programs. Local residents have improved their skills by learning with the training programs offered by the OUC.Originality/valueODE is proved to be an effective way to eradicate poverty. Open universities are proved to be able to make contributions to social justice. By fulfilling its commitments to eliminate poverty within the national strategy framework, the OUC has built its brand nationwide.

A bagging dynamic deep learning network for diagnosing COVID-19.

COVID-19 is a serious ongoing worldwide pandemic. Using X-ray chest radiography images for automatically diagnosing COVID-19 is an effective and convenient means of providing diagnostic assistance to clinicians in practice. This paper proposes a bagging dynamic deep learning network (B-DDLN) for diagnosing COVID-19 by intelligently recognizing its symptoms in X-ray chest radiography images. After a series of preprocessing steps for images, we pre-train convolution blocks as a feature extractor. For the extracted features, a bagging dynamic learning network classifier is trained based on neural dynamic learning algorithm and bagging algorithm. B-DDLN connects the feature extractor and bagging classifier in series. Experimental results verify that the proposed B-DDLN achieves 98.8889% testing accuracy, which shows the best diagnosis performance among the existing state-of-the-art methods on the open image set. It also provides evidence for further detection and treatment.

Near-Infrared Light Brightens Bacterial Disinfection: Recent Progress and Perspectives.

Bacterial infection is a universal threat to public health, which not only causes many serious diseases but also exacerbates the condition of the patients of cancer, pandemic diseases, e.g., COVID-19, and so on. Antibiotic therapy has been used to be an effective way for common bacterial disinfection. However, due to the misuse and abuse of antibiotics, more and more antibiotic-resistant bacteria have emerged as fatal threats to human beings. At present, more than 700,000 patients die every year with bacterial infections because of the lack of effective treatment. It is frustrating that the pace of development of antibiotics lags far behind that of bacterial resistance, with an estimation of 10 million deaths per year from bacterial infections after 2050. Facing such a rigorous challenge, approaches for bacterial disinfection are urgently demanded. The recently developed near-infrared (NIR) light-irradiation-based bacterial disinfection is highly promising to shatter bacterial resistance by employing NIR light-responsive materials as mediums to generate antibacterial factors such as heat, reactive oxygen species (ROS), and so on. This treatment approach is proved to be a potent candidate to accurately realize spatiotemporal control, while effectively eradicating multidrug-resistant bacteria and inhibiting antibiotic resistance. Herein, we summarize the latest progress of NIR light-based bacterial disinfection. Ultimately, current challenges and perspectives in this field are discussed.