For the study, published in the journal Nature Machine Intelligence, researchers examined a database of blood samples from 485 infected patients in Wuhan, China. They used machine learning tools to pinpoint the biomarkers that can help predict death from COVID-19.
They found that lactic dehydrogenase, lymphocyte and high-sensitivity C-reactive protein can all help predict a patient’s death.
An increase in lactic dehydrogenase is regarded as a common sign of tissue/cell damage, while an increase in high-sensitivity C-reactive protein indicates inflammation and is an important marker for poor outcomes in acute respiratory distress syndromes. Low levels of lymphocytes, white blood cells that are one of the main types of immune cells in the body, has been linked to severe COVID-19 disease and death.
The biomarkers can help predict death more than 10 days in advance with more than 90 percent accuracy, researchers said.
More articles on patient safety & outcomes:
COVID-19 nearly triples death risk of cancer patients, study finds
6 insights into COVID-19 patient care patterns worldwide
COVID-19 is 13 times deadlier than flu, study suggests
