Researchers at Cleveland Clinic have developed the first prediction model to forecast the likelihood of patients testing positive for COVID-19 and the potential disease outcomes.
Five things to know:
1. The risk prediction model makes projections based on age, race, gender, socioeconomic status, vaccination history and current medications. Healthcare providers can use the tool to help them make decisions about care, especially as the demand for limited testing resources has increased.
2. Cleveland Clinic researchers developed the tool, nomogram, with data from about 12,000 patients enrolled in its COVID-19 registry. The data includes patients that tested positive and negative for the disease. The data scientists then used statistical algorithms to move the registry data from the EHR into the nomogram.
3. The nomogram is available freely online as a risk calculator, which can be found here. The research registry now has data from more than 23,000 patients and is being used across the health system in more than 140 COVID-19-related research projects.
4. A study conducted using the data found that patients who received the pneumococcal polysaccharide vaccine and flu vaccine were less likely to test positive for COVID-19 than patients who didn't receive the vaccinations. Patients taking melatonin were also less likely to test positive than patients who weren't taking it. The study is published in the journal Chest.
5. Cleveland Clinic previously developed a nomogram based on patient data collected before April 2, and it showed reliability when used in other regions, including Florida.
"This nomogram will bring precision medicine to the COVID-19 pandemic, helping to enable researchers and physicians to predict an individual’s risk of testing positive," said Michael Kattan, PhD, chair of Lerner Research Institute's department of quantitative health sciences at Cleveland Clinic. "Additionally, while testing solutions continue to be needed, it is so important to make sure we are responsibly and optimally dispatching our resources — including clinical personnel, personal protective equipment and hospital beds. Our risk- prediction model stands to greatly assist hospital systems in this planning."
More articles on data analytics:
How NYC Health + Hospitals combined data streams, clinical expertise for 'epidemic intelligence' efforts
Cleveland Clinic receives $7.2M NIH grant to study MS diagnostics
Apple updates sharing options on COVID-19 app