Study: AI predicts which COVID-19 patients will develop severe respiratory disease

Editor's Note

In this study, researchers from NYU Grossman School of Medicine and the Courant Institute of Mathematical Sciences at New York University, in partnership with Wenzhou Central Hospital and Cangnan People’s Hospital in Wenzhou, China, developed an artificial intelligence (AI) framework that accurately predicted which patients newly infected with the SARS-CoV-2 virus would go on to develop acute respiratory distress syndrome (ARDS).

Characteristics considered to be markers for COVID-19, such as patterns seen in lung images, fever, strong immune responses, age, and gender were not useful in predicting which patients with initial, mild symptoms would develop ARDS.

Instead, the AI framework found that three factors were accurately predictive of severe disease:

• a mildly elevated alanine aminotransferase (liver enzyme)
• the presence of myalgias (body aches)
• an elevated hemoglobin (red blood cells).

The AI framework achieved 70% to 80% accuracy in predicting which patients would develop ARDS.

The researchers say they hope the framework, when fully developed, will be useful to physicians as they assess which moderately ill patients really need beds, and who can safely go home.