No abstract

The Coronavirus disease 2019 (COVID-19) presents open questions in how we clinically diagnose and assess disease course. Recently, chest computed tomography (CT) has shown utility for COVID-19 diagnosis. In this study, we developed Deep COVID DeteCT (DCD), a deep learning convolutional neural network (CNN) that uses the entire chest CT volume to automatically predict COVID-19 (COVID+) from non-COVID-19 (COVID−) pneumonia and normal controls. We discuss training strategies and differences in performance across 13 international institutions and 8 countries. The inclusion of non-China sites in training significantly improved classification performance with area under the curve (AUCs) and accuracies above 0.8 on most test sites. Furthermore, using available follow-up scans, we investigate methods to track patient disease course and predict prognosis.

No abstract

While severe acute respiratory syndrome coronavirus 2 (SARS‐CoV‐2) infection primarily causes inflammation in the respiratory system, there is growing evidence of extrapulmonary tissue damage mediated by the host innate immune system in children and adults. A cytokine storm can manifest as a viral‐induced haemophagocytic lymphohistiocytosis (HLH). Here, we present a previously healthy 8‐year‐old boy with newly diagnosed cardiac injury and COVID‐19‐related HLH syndrome with haemophagocytosis in bone marrow biopsy. After remission of inflammation, the patient underwent a heart transplant due to persistent cardiac failure. The histology of the explanted heart showed only a focal subtle subendocardial inflammation. Three days after transplant, he developed progressive acute respiratory distress syndrome (ARDS) with the rise of inflammatory markers. He unfortunately died after 20 days because of disseminated intravascular coagulation (DIC). For the first time, we described a child with COVID‐19‐related HLH and severe cardiac failure, which had a poor prognosis despite a heart transplant.