The results of the research project were published in the "Nature Machine Intelligence" scientific journal.
According to the abstract of the research paper, the study uses a database of blood samples from 485 infected patients in the region of Wuhan to identify "crucial predictive biomarkers of disease mortality."
"Machine learning tools selected three biomarkers that predict the mortality of individual patients more than 10 days in advance with more than 90% accuracy: lactic dehydrogenase (LDH), lymphocyte and high-sensitivity C-reactive protein (hs-CRP)," the abstract reads.
The study for instance found that "relatively high levels of LDH alone seem to play a crucial role in distinguishing the vast majority of cases that require immediate medical attention." LDH is an enzyme found in almost every cell of the human body, including blood.
The full research paper is available here.
