Researchers at Cleveland Clinic have developed a risk-prediction model healthcare providers can use to forecast a patient's likelihood of testing positive for COVID-19, as well as their outcomes from the disease, according to a news release.
Nomogram, the risk-prediction model, shows the relevance of age, race, gender, socioeconomic status, vaccination history and current medications in COVID-19 risk, according to a new study published in the medical journal CHEST. The risk calculator is freely available online.
The tool offers a more scientific approach for healthcare providers to predict patient risk and then tailor decisions about their care. This is important given the increased demand for testing and limited resources, according to the release.
"The ability to accurately predict whether or not a patient is likely to test positive for COVID-19, as well as potential outcomes including disease severity and hospitalization, will be paramount in effectively managing our resources and triaging care," said Dr. Lara Jehi, Cleveland Clinic's chief research information officer and corresponding author on the study, in a provided statement. "As we continue to battle this pandemic and prepare for a potential second wave, understanding a person's risk is the first step in potential care and treatment planning."
Michael Kattan, chair of Lerner Research Institute's Department of Quantitative Health Sciences, was a study co-author.
Nomogram was developed with statistical algorithms using data from nearly 12,000 patients enrolled in the Clinic's COVID-19 registry, which includes all individuals tested at Cleveland Clinic for the disease, not just those that test positive, according to the release. The COVID-19 research registry now has data from more than 23,000 patients and is being used in a variety of studies.
The tool was developed using data from patients tested for COVID-19 at the Clinic for April 2 and showed good performance and reliability when used in Florida and when used over time (patients tested after April 2), according to the release, which notes that this suggests the patterns and predictors identified in the model are consistent across regions/communities and could be adopted for clinical practice across the country.
"Our findings corroborated several risk factors already reported in existing literature — including that being male and of advancing age both increase the likelihood of testing positive for COVID-19 — but we also put forth some new associations," Jehi said. "Further validation and research are needed into these initial insights, but these correlations are extremely intriguing."
The study revealed several novel insights into disease risk, including, according to the release:
- Patients who received the pneumococcal polysaccharide (PPSV23) and flu vaccines are less likely to test positive for COVID-19 than those who have not.
- Patients actively taking melatonin (over-the-counter sleep aid), carvedilol (treatment for high blood pressure and heart failure) or paroxetine (antidepressant) are less likely to test positive than patients who aren't taking the drugs.
- Patients of low socioeconomic status, which in this study was measured by ZIP code, are more likely to test positive than patients of greater economic means.
- Patients of Asian descent are less likely than Caucasian patients to test positive.
A previous network medicine study led by Lerner Research Institute scientists identified 16 drugs and three drug combinations as candidates for repurposing as potential COVID-19 treatments. The findings indicate an association between taking these medications and reduced risk of testing positive for COVID-19, but more studies are needed to assess how the drugs affect disease progression, according to the release.
This article was originally published in Crain's Cleveland Business.
