A university-clustered tuberculosis outbreak during the COVID-19 pandemic in eastern China.

During the COVID-19 pandemic in 2020, a tuberculosis outbreak occurred in a university in eastern China, with 4,488 students and 421 staff on the campus. A 19-year-old student was diagnosed in August 2019. Later, the first round of screening was initiated among close contacts, but no active cases were found. Till September 2020, four rounds of screening were performed. Four rounds of screening were conducted on September 9, November 8, November 22-25 in 2019 and September 2020, with 0, 5, 0 and 43 cases identified, respectively. A total of 66 active tuberculosis were found in the same university, including 4 sputum culture-positive and 7 sputum smear-positive. The total attack rate of active tuberculosis was 1.34% (66/4909). The whole-genome sequencing showed that the isolates belonged to the same L2 sub-specie and were sensitive to all tested antituberculosis drugs. Delay detection, diagnosis and report of cases were the major cause of this university tuberculosis epidemic. More attention should be paid to the asymptomatic students in the index class. After the occurrence of tuberculosis cases in schools, multiple rounds of screening should be carried out, and preventive therapy should be applied in a timely manner.

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.