Artificial intelligence used to predict which coronavirus patients are at greater risk

A molecular geneticist in protective clothing prepares a test for SARS-CoV-2 coronavirus which causes the COVID-19 disease in a hospital lab in the Rhineland Region, Germany. EPA-EFE/SASCHA STEINBACH

Reading Time: < 1 minute


An artificial intelligence tool is being developed which researchers hope could be used to predict which coronavirus patients will suffer life-threatening lung damage.

The team behind the initial study reported 80% accuracy in its predictions of which patients would develop acute respiratory distress syndrome (ARDS) – which can be fatal in severe COVID-19 cases.

The aim of the research is to provide hospitals with a tool to help decide which patients cans safely be sent home and which will need beds and potentially breathing equipment allocated to them.

The AI tool used data on 53 patients from two hospitals in China, who all tested positive for coronavirus in January.

ARDS is a condition where the lungs, inflamed by serious infection such as pneumonia, cannot provide the body’s vital organs with enough oxygen. The condition causes fluid to to leak into the air sacs in the lungs, making it difficult to breath.

It is the cause of death in many fatal coronavirus cases, with severe cases of pneumonia damaging the lungs of patients. In one study published earlier this month, of 201 patients with pneumonia in a hospital in China, 84 developed ARDS, 67 received mechanical ventilation and 44 died. All those who died developed ARDS and received mechanical ventilation.

The AI study, conducted by researchers at NYU Grossman School of Medicine and the Courant Institute of Mathematical Sciences at New York University, looked at demographic, laboratory and radiological findings of patients with COVID-19.

Read more via Euronews

%d bloggers like this: