Mar 23, Vasanth Venugopal and Vidur Mahajan
A recent study in Radiology suggests that AI may be able to distinguish pneumonia caused by COVID-19 from community-acquired pneumonia on chest CT scans. Despite the strengths of this study, two key limitations remain. In any case, diagnosing COVID-19 on CT scans is difficult for humans and AI, and currently the CDC advises against its use as a first-line diagnostic tool. However, this doesn’t mean CT is useless in this pandemic. For instance, serial CT scans could help predict prognosis and/or clinical course of certain patients—which would be able to not only guide treatment but also help triage cases in a situation where healthcare systems are overburdened.
Mar 24, Phuoc Le, Connie Chan and Brooke Warren
“Even a small number of patients showing up in the emergency room all at once could quickly overwhelm tiny rural hospitals. Testing isn’t as simple as running a swab over to a nearby public health lab — a courier has to pick up the samples once a day and drive them hundreds of miles,” as one rural ER provider explained. We need to protect our rural tribal communities who have additional vulnerabilities. These barriers are only compounded by the fact that American Indian/Alaskan Native populations have higher rates of underlying health conditions, putting them at greater risk for morbidity and mortality in the face of COVID-19.
Mar 26, Stephen Borstelmann
After you have scanned a patient for COVID, how long would the room be down? While CT scanning was an important diagnostic tool in the early days in Wuhan, today radiologists do not believe that CT scanning has a role in COVID diagnosis. Part of the reason is the concern of transmission of COVID to other patients or healthcare workers via the radiology department, along with the fact that we now have better and faster PCR tests as the pandemic has evolved. So, how does imaging play a role in COVID-19 and how can we properly perform infection control in radiology and beyond?