New COVID-19 prediction model can help determine disease progression

Anuja Vaidya for Becker’s Hospital Review

Researchers from Baltimore-based Johns Hopkins Medicine have developed a prediction model to help clinicians forecast if a coronavirus patient’s conditions are likely to worsen.

To develop the model, the researchers used data collected from 827 COVID-19 patients admitted to five Johns Hopkins hospitals between March 4 and April 24. They wrote about the model in the journal Annals of Internal Medicine.

The model, called the COVID Inpatient Risk Calculator, is available online. It takes into account several disease risk factors, including age, body mass index, lung health, vital signs and the severity of the patient’s COVID-19 symptoms at the time of admission.

“Different combinations of risk factors appear to predict severe disease or death, with probabilities ranging from over 90 percent to as little as 5 percent,” Brian Garibaldi, MD, associate professor of medicine at the Johns Hopkins University School of Medicine and leader of the research team, wrote in the journal.

The prediction model can be used to make decisions about care planning and resource allocation, the researchers said.