New tool identifies severe COVID-19 patients at risk for death, researchers say

Feb. 28 (UPI) -- A new data analysis tool developed by researchers at Yale University has identified specific immune cell types that can be used to spot people at increased risk for death from COVID-19, they said in an article published Monday by the journal Nature Biotechnology.

The Multiscale PHATE tool can analyze millions of cells within minutes using an algorithm called PHATE, or Potential of Heat-diffusion for Affinity-based Transition Embedding, the researchers said.

The machine-learning tool enables researchers to track cell development and spot changes in cell production instantly, they said.

Using the tool, they analyzed 55 million blood cells taken from 163 patients with severe COVID-19 admitted to Yale New Haven Hospital and found that high levels T cells helped prevent death from the disease.

Conversely, high levels of two white blood cell types known as granulocytes and monocytes were associated with higher risk for death in people with severe COVID-19, the data showed.

By measuring levels of these cells in the blood, the Yale researchers accurately predicted whether patients lived or died 83% of the time, they said.

In theory, the new data analytical tool could be used to fine tune risk assessment in a host of diseases, Smita Krishnaswamy, an associate professor of genetics and computer science at Yale University and one of the developers of the Multiscale PHATE tool, said in a news release.

"We were able to rank order risk factors of mortality to show which are the most dangerous," she said.

Immune cells such as T cells and B cells are known to provide broad protection against viruses, including the one that causes COVID-19, according to the Centers for Disease Control and Prevention.

These white blood cells are involved in the production of antibodies, or proteins that help the immune system fight off viruses, the agency says.

Vaccines against viruses, including those developed to fight COVID-19, are designed to boost production of antibodies, it says.

However, in COVID-19, some immune cell responses, including those that are normally protective against other viruses, can occasionally trigger deadly inflammation and death in patients, according to the Yale researchers.

Previous studies have identified several proteins that, at high blood levels, appear to increase a person's risk for death from COVID-19.

Using Multiscale PHATE, they found that a type of T cell called TH17 was associated with higher mortality in COVID-19 patients when clustered with the immune system cells IL-17 and IFNG, they said.

"Machine-learning algorithms typically focus on a single resolution view of the data, ignoring information that can be found in other more focused views," study co-author Manik Kuchroo said in the press release.

"For this reason, we created Multiscale PHATE, which allows users to zoom in and focus on specific subsets of their data to perform more detailed analysis," said Kuchroo, a doctoral candidate at Yale School of Medicine, who helped develop the technology.