Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine
-
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.
-
Several reports had observed a high risk of pulmonary embolism (PE) in patients with coronavirus disease 2019 (COVID-19), most of them in the intensive care unit. Reported findings indicate that a direct viral-mediated hyperinflammatory response leads to local thromboinflammation. According to those findings, the incidence of deep venous thrombosis (DVT) in patients with COVID-19 and PE should be low. The objective of this study was to evaluate the incidence of DVT in patients with COVID-19 who developed PE. ⋯ Our study showed a low incidence of DVT in a cohort of patients with COVID-19 and PE. This observation suggests that PE in these patients could be produced mainly by a local thromboinflammatory syndrome induced by severe acute respiratory syndrome coronavirus 2 infection and not by a thromboembolic event.
-
The purpose of this study was to evaluate the performance of a handheld ultrasound device for difficult peripheral intravenous (PIV) access performed by nurses and paramedics in the emergency department (ED). ⋯ The handheld ultrasound device performed well in terms of usability and reliability for PIV access.