The value of longitudinal clinical data and paired CT scans in predicting the deterioration of COVID-19 revealed by an artificial intelligence system.

The respective value of clinical data and CT examinations in predicting COVID-19 progression is unclear, because the CT scans and clinical data previously used are not synchronized in time. To address this issue, we collected 119 COVID-19 patients with 341 longitudinal CT scans and paired clinical data, and we developed an AI system for the prediction of COVID-19 deterioration. By combining features extracted from CT and clinical data with our system, we can predict whether a patient will develop severe symptoms during hospitalization. Complementary to clinical data, CT examinations show significant add-on values for the prediction of COVID-19 progression in the early stage of COVID-19, especially in the 6th to 8th day after the symptom onset, indicating that this is the ideal time window for the introduction of CT examinations. We release our AI system to provide clinicians with additional assistance to optimize CT usage in the clinical workflow.

An AI-based auxiliary empirical antibiotic therapy model for children with bacterial pneumonia using low-dose chest CT images.

PURPOSE: To construct an auxiliary empirical antibiotic therapy (EAT) multi-class classification model for children with bacterial pneumonia using radiomics features based on artificial intelligence and low-dose chest CT images. MATERIALS AND METHODS: Data were retrospectively collected from children with pathogen-confirmed bacterial pneumonia including Gram-positive bacterial pneumonia (122/389, 31%), Gram-negative bacterial pneumonia (159/389, 41%) and atypical bacterial pneumonia (108/389, 28%) from January 1 to June 30, 2019. Nine machine-learning models were separately evaluated based on radiomics features extracted from CT images; three optimal submodels were constructed and integrated to form a multi-class classification model. RESULTS: We selected five features to develop three radiomics submodels: a Gram-positive model, a Gram-negative model and an atypical model. The comprehensive radiomics model using support vector machine method yielded an average area under the curve (AUC) of 0.75 [95% confidence interval (CI), 0.65-0.83] and accuracy (ACC) of 0.58 [sensitivity (SEN), 0.57; specificity (SPE), 0.78] in the training set, and an average AUC of 0.73 (95% CI 0.61-0.79) and ACC of 0.54 (SEN, 0.52; SPE, 0.75) in the test set. CONCLUSION: This auxiliary EAT radiomics multi-class classification model was deserved to be researched in differential diagnosing bacterial pneumonias in children.

Dynamics of neutralizing antibody responses to SARS-CoV-2 in patients with COVID-19: an observational study.

Our understanding of the protective immunity, particularly the long-term dynamics of neutralizing antibody (NAbs) response to SARS-CoV-2, is currently limited. We enrolled a cohort of 545 COVID-19 patients from Hubei, China, who were followed up up to 7 months, and determined the dynamics of NAbs to SARS-CoV-2 by using a surrogate virus neutralization test (sVNT). In our validation study, sVNT IC50 titers and the neutralization rate measured at a single dilution (1:20) were well correlated with FRNT titers (r = 0.85 and 0.84, respectively). The median time to seroconversion of NAbs was 5.5 days post onset of symptoms. The rate of positive sVNT was 52% in the first week, reached 100% in the third week, and remained above 97% till 6 months post onset. Quantitatively, NAbs peaked in the fourth week and only a quarter of patients had an estimated peak titer of >1000. NAbs declined with a half-time of 61 days (95% CI: 49-80 days) within the first two months, and the decay deaccelerated to a half-time of 104 days (95% CI: 86-130 days) afterward. The peak levels of NAbs were positively associated with severity of COVID-19 and age, while negatively associated with serum albumin levels. The observation that the low-moderate peak neutralizing activity and fast decay of NAbs in most naturally infected individuals called for caution in evaluating the feasibility of antibody-based therapy and vaccine durability. NAbs response positively correlated with disease severity, warning for the possibility of repeat infection in patients with mild COVID-19.

Viral and Antibody Kinetics of COVID-19 Patients with Different Disease Severities in Acute and Convalescent Phases: A 6-Month Follow-Up Study.

Coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has spread rapidly around the world, posing a major threat to human health and the economy. Currently, long-term data on viral shedding and the serum antibody responses in COVID-19 patients are still limited. Herein, we report the clinical features, viral RNA loads, and serum antibody levels in a cohort of 112 COVID-19 patients admitted to the Honghu People's Hospital, Hubei Province, China. Overall, 5.36% (6/112) of patients showed persistent viral RNA shedding (> 45 days). The peak viral load was higher in the severe disease group than in the mild group (median cycle threshold value, 36.4 versus 31.5; P = 0.002). For most patients the disappearance of IgM antibodies occurred approximately 4-6 weeks after symptoms onset, while IgG persisted for over 194 days after the onset of symptoms, although patients showed a 46% reduction in antibodies titres against SARS-CoV-2 nucleocapsid protein compared with the acute phase. We also studied 18 asymptomatic individuals with RT-qPCR confirmed SARS-CoV-2 infection together with 17 symptomatic patients, and the asymptomatic individuals were the close contacts of these symptomatic cases. Delayed IgG seroconversion and lower IgM seropositive rates were observed in asymptomatic individuals. These data indicate that higher viral loads and stronger antibody responses are related to more severe disease status in patients with SARS-CoV-2 infection, and the antibodies persisted in the recovered patient for more than 6 months so that the vaccine may provide protection against SARS-CoV-2 infection.

COVID-19: A review of what radiologists need to know.

Coronavirus disease-2019 (COVID-19) is spreading throughout the world. Chest radiography and computed tomography play an important role in disease diagnosis, differential diagnosis, severity evaluation, prognosis prediction, therapeutic effects assessment and follow-up of patients with COVID-19. In this review, we summarize knowledge of COVID-19 pneumonia that may help improve the abilities of radiologists to diagnose and evaluate this highly infectious disease, which is essential for epidemic control and preventing new outbreaks in the short term.

COVID-19 in China: From epidemiology to treatment (Review).

Coronavirus disease 2019 (COVID-19) is a newly emerging infectious disease caused by the novel coronavirus SARS-CoV-2. It first became prevalent in Wuhan, Hubei, China in December 2019. COVID-19 was initially characterized by pneumonia of unknown etiology, accompanied by fever, dry cough and fatigue. Due to its highly infectious nature it rapidly led to widespread human infection, causing 80,924 confirmed cases and 3,140 mortalities in mainland China as of March 9, 2020. The present review highlights the prevalence of COVID-19 in China, the etiology, pathology, clinical presentation, laboratory and chest imaging tests, and treatment of this disease.