Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine
-
Coronavirus disease 2019 (COVID-19) represents a very heterogeneous disease. Some aspects of COVID-19 pneumonia question the real nature of ground glass opacities and its consolidative lesions. It has been hypothesized that COVID-19 lung involvement could represent not only a viral effect but also an immune response induced by the infection, causing epithelial/endothelial lesions and coagulation disorders. We report 3 cases of COVID-19 pneumonia in which contrast-enhanced ultrasound was suggestive of consolidations with perfusion defects, at least in part caused by ischemic or necrotic changes and not only by inflammatory or atelectasis events.
-
Scarce data exist regarding the natural history of lung lesions detected on ultrasound in those who survive severe COVID-19 pneumonia.
-
Case Reports
Usefulness of Lung Ultrasound Follow-up in Patients Who Have Recovered From Coronavirus Disease 2019.
Coronavirus disease 2019 is caused by severe acute respiratory syndrome coronavirus 2 infection, which tends to be mild. Even in these cases, our understanding is still incomplete, particularly regarding its sequelae and long-term outcomes. ⋯ It is possible to correlate the findings from lung ultrasound with the symptoms and the fibrosis or residual abnormalities present on chest computed tomography. Lung ultrasound, which is easy to use, without side effects or radiation, helps monitor the disease resolution or assess early progression to lung fibrosis, as exemplified in the cases reported.
-
We evaluated the utility of focused cardiac ultrasound to predict the length of stay in patients presenting to the emergency department with dyspnea of unclear etiology. ⋯ Focused cardiac ultrasound and calculation of a FLUID score for patients with undifferentiated dyspnea can be a powerful tool to predict the hospital length of stay.
-
To create a deep learning algorithm capable of video classification, using a long short-term memory (LSTM) network, to analyze collapsibility of the inferior vena cava (IVC) to predict fluid responsiveness in critically ill patients. ⋯ We demonstrated that an LSTM network can be trained by using videos of IVC US to classify IVC collapse to predict fluid responsiveness. Our LSTM network performed moderately well given the small training cohort but worse than point-of-care US experts. Further training and testing of the LSTM network with a larger data sets is warranted.