ABSTRACT
Background In this study, we aimed to compare two outbreaks of coronavirus disease 2019 (COVID-19) in Belgium in tomographic and biological-clinical aspects with artificial intelligence (AI). Methodology We performed an observational retrospective study. Adult patients who were symptomatic in the first seven days with COVID-19 infection, diagnosed by chest computed tomography (CT) and/or reverse transcription-polymerase chain reaction, were included in this study. The first wave of the pandemic lasted from March 25, 2020, to May 25, 2020, and the second wave lasted from October 7, 2020, to December 7, 2020. For each wave, two subgroups were defined depending on whether respiratory failure occurred during the course of the disease. The quantitative estimation of COVID-19 lung lesions was performed by AI, radiologists, and radiology residents. The chest CT severity score was calculated by AI. Results In the 202 patients included in this study, we found statistically significant differences for obesity, hypertension, and asthma. The differences were predominant in the second wave. Moreover, a mixed distribution (central and peripherical) of pulmonary lesions was noted in the second wave, but no differences were noted regarding mortality, respiratory failure, complications, and other radiological and biological elements. Chest CT severity score was among the risk factors of mortality and respiratory failure. There was a mild agreement between AI and visual evaluation of pulmonary lesion extension (K = 0.4). Conclusions Between March and December 2020, in our cohort, for the majority of the parameters analyzed, we did not record significant changes between the two waves. AI can reduce the experience and performance gap of radiologists and better establish a hospitalization criterion.
ABSTRACT
BACKGROUND: Susceptibility to Covid-19 has been found to be associated with the ABO blood group, with O type individuals being at a lower risk. However, the underlying mechanism has not been elucidated. Here, we aimed to test the hypothesis that Covid-19 patients might have lower levels of ABO antibodies than non-infected individuals as they could offer some degree of protection. METHODS: After showing that the viral spike protein harbors the ABO glycan epitopes when produced by cells expressing the relevant glycosyltransferases, like upper respiratory tract epithelial cells, we enrolled 290 patients with Covid-19 and 276 asymptomatic controls to compare their levels of natural ABO blood group antibodies. RESULTS: We found significantly lower IgM anti-A + anti-B agglutination scores in blood group O patients (76.93 vs 88.29, P-value = 0.034) and lower levels of anti-B (24.93 vs 30.40, P-value = 0.028) and anti-A antibodies (28.56 vs 36.50, P-value = 0.048) in blood group A and blood group B patients, respectively, compared to controls. CONCLUSION: In this study, we showed that ABO antibody levels are significantly lower in Covid-19 patients compared to controls. These findings could indicate that patients with low levels of ABO antibodies are at higher risk of being infected.