Scientists develop tool to identify patients most at risk of dying from COVID | World News
Scientists have developed an algorithm to identify people who are most at risk of dying from COVID while being treated in a hospital.
The COVID-19 Disease Outcomes Predictor (CODOP) will help provide early warning to doctors about who needs serious care.
The system uses 12 blood molecules that are normally collected at the hospital when a patient is admitted – meaning the algorithm will be easily adopted by healthcare systems around the world.
CODOP uses artificial intelligence and can identify which patients face a poor prognosis, according to research published in eLife.
It found that the algorithm could predict the survival or death of hospitalized patients with high accuracy up to nine days before either outcome occurred.
Along with helping doctors make decisions about the patients who need the most care and the route of treatment, it can also help countries access fewer resources.
The study’s senior author and international project leader said new variants, diminished immunity and an easing of safety measures “means we could continue to see increase in infections and hospitalizations”.
He added: “There is a need for general and clinically valid triage tools to assist in allocating hospital resources to COVID-19especially in places where resources are scarce.
“But these tools need to be able to deal with the ever-changing scenario of a global pandemic and must be easy to implement.”
Dogs can be trained to detect COVID
The data used were from routine blood samples obtained from nearly 30,000 patients at more than 150 hospitals in Spain, the US, Bolivia, Honduras and Argentina between March 2020 and February 2022.
This allowed the researchers to collect information from vaccinated and unvaccinated people with natural immunity and mention the occurrence of different variants, including Omicron.