AI predicts COVID prognosis at near-expert level using CT scoring system

New research details how a deep convolutional neural network (dCNN) uses a scoring system to predict prognosis for COVID inpatients at a nearly expert level based off CT scans. 

The dCNN forecasted hospital stay, intensive care unit admission and intubation with an interobserver agreement of 0.892 when scoring chest CT images from hospitalized patients with COVID pneumonia. Experts involved in the study suggest that the dCNN could assist clinicians who treat COVID patients with assessing disease severity and other prognostic factors that might direct treatment plans. 

“The use of…