Scientists have developed an algorithm to identify people most at risk of dying from COVID when treated in a hospital.
The COVID-19 Outcome Predictor (CODOP) will help provide early warning to clinicians about who needs intensive care.
The system uses 12 blood molecules that are typically collected in a hospital when a patient is admitted, meaning the algorithm should be easily adopted by healthcare systems around the world.
According to a study published in eLife, CODOP uses artificial intelligence to determine which patients have a poor prognosis.
The algorithm was found to be able to predict the survival or death of hospitalized patients with high accuracy up to nine days before any outcome occurs.
As well as helping doctors make decisions about patients who need the most intensive care and treatment options, it can also help countries that have access to fewer resources.
The study’s senior author and international project leader said the new options, weakened immunity, and loosened security measures “mean we are likely to continue to see spikes in infections and hospitalizations.”
He added: “There is a need for clinically valuable and versatile triage tools to help allocate hospital resources to COVID-19, especially in places with limited resources.
“But these tools need to be able to handle an ever-changing global pandemic scenario and be easy to apply.”
We used data from routine blood samples taken from nearly 30,000 patients at more than 150 hospitals in Spain, the United States, Bolivia, Honduras, and Argentina between March 2020 and February 2022.
This allowed the researchers to gather information from vaccinated, unvaccinated, and natural immune individuals and capture the emergence of various variants, including Omicron.