ABSTRACT
Objective@#To study the effect of low-to-moderate dose glucocorticoid therapy on viral clearance time in patients with COVID-19.@*Methods@#A total of 72 patients diagnosed with COVID-19 from January 19 to February 17, 2020 at the First Affiliated Hospital, School of Medicine, Zhejiang University were recruited. All patients received oral abidol and/or combined lopinavir/ritonavir, darunavir antiviral, and symptomatic supportive care. Among them, 51 patients received methylprednisolone (0.75-1.50 mg·kg-1·d-1) (glucocorticoid treatment group), and 21 patients who did not use glucocorticoid were the control group. The time of stable virologic conversion insputumand the time of radiologic recovery in lungsince onset were compared between the two groups and among the normal patients.The Kruskal-Wallis test or Fisher exact test was used to compare the difference between groups.@*Results@#The median ages of the glucocorticoid group and the control group were 52 [interquartile range (IQR):45, 62] years and 46 (IQR: 32, 56)years, and the differences were significant (P<0.05). The clinical conditions at hospital admission were different between the two groups (P<0.01). There were 52.0% critical ill patients in the glucocorticoid treatment group, compared to that of 71.4% normal patients in the control group. The median times from the onset tostable virologic conversion to negative in the two groups were 15 (IQR:13,20) days and 14 (IQR:12,20) days (P>0.05), and the difference was no statistically significant. The median times from onset to radiologic recovery were 13 (IQR: 11,15) days and 13 (IQR:12,17) days in the two groups, and there was no difference (P>0.05). In ordinary patients, the median timesfrom the onset tostable virologic conversion insputum were no difference (P>0.05), with 13 (IQR:11,18) days in the glucocorticoid group and 13 (IQR:12,15) days in the control group; The median times from onset to radiologic recovery in lungwere also no difference (P>0.05), with 12 (IQR: 10,15)days in the glucocorticoid group and 13 (IQR: 12,17) days inthe control group.@*Conclusions@#Low-to-moderate glucocorticoid treatment has no effect on the time of virus clearance in patients with different clinical types of COVID-19. The glucocorticoid is not recommended since no effectiveness on accelerating the improvement of radiologic recovery in lung has been observed.
ABSTRACT
We found that the real time reverse transcription-polymerase chain reaction (RT-PCR) detection of viral RNA from sputum or nasopharyngeal swab has a relatively low positive rate in the early stage to determine COVID-19 (named by the World Health Organization). The manifestations of computed tomography (CT) imaging of COVID-19 had their own characteristics, which are different from other types of viral pneumonia, such as Influenza-A viral pneumonia. Therefore, clinical doctors call for another early diagnostic criteria for this new type of pneumonia as soon as possible.This study aimed to establish an early screening model to distinguish COVID-19 pneumonia from Influenza-A viral pneumonia and healthy cases with pulmonary CT images using deep learning techniques. The candidate infection regions were first segmented out using a 3-dimensional deep learning model from pulmonary CT image set. These separated images were then categorized into COVID-19, Influenza-A viral pneumonia and irrelevant to infection groups, together with the corresponding confidence scores using a location-attention classification model. Finally the infection type and total confidence score of this CT case were calculated with Noisy-or Bayesian function.The experiments result of benchmark dataset showed that the overall accuracy was 86.7 % from the perspective of CT cases as a whole.The deep learning models established in this study were effective for the early screening of COVID-19 patients and demonstrated to be a promising supplementary diagnostic method for frontline clinical doctors.