In a new study, researchers created a model that uses a trio of biological markers to predict whether a patient was likely to die from COVID-19.
The model was able to forecast the death of individual patients more than 10 days in advance with at least 90% accuracy.
To identify commonalities between these severe cases, the researchers analyzed blood samples taken repeatedly from 485 coronavirus patients at Tongji Hospital in Wuhan, China, between January 10 and February 18. They tested for myriad kidney, heart, and blood-clotting issues, noted whether those patients had survived or died, then used machine-learning algorithms to look for biological patterns.
The results found that the following indicators can predict whether a patient had a higher risk of death than other infected people: