A COVID-19 patient’s blood sample can predict survival weeks in advance.

Using blood samples taken at 349 timepoints from critically ill COVID-19 patients, researchers studied the levels of 321 proteins that can help predict survival, weeks before the outcome.

Healthcare systems all over the world are having to cope with large numbers of critically ill COVID-19 patients who require specialized medical care, especially if they are considered high-risk. Clinically accepted risk assessments in critical care medicine, such as the SOFA or APACHE II, have only limited predictive value for COVID-19.

Now, new research, published this week in the open-access journal PLOS Digital Health by Florian Kurth and Markus Ralser of the Charité – Universitätsmedizin Berlin, Germany, and colleagues, suggests that a single blood sample taken from a severely ill COVID-19 patient can be analyzed by a machine learning model that uses blood plasma proteins to predict survival weeks before the outcome.

The current study examined the levels of 321 proteins in blood samples taken at 349 timepoints from 50 severely ill COVID-19 patients being treated in two separate health care facilities in Germany and Austria. The researcher employed a machine learning approach to discover links between the measured proteins and patient survival.

The average period from admission to death was 28 days, and 15 of the patients in the cohort died. The median length of stay in the hospital for those who survived was 63 days.

The researchers identified 14 proteins that changed in opposite directions for patients who survived intensive care compared to individuals who did not.

The researchers then created a machine learning model to predict survival based on a single time-point measurement of key proteins, which they evaluated on an independent validation cohort of 24 COVID-10 patients.

In this cohort, the model showed good predictive power, correctly predicting the outcome for 18 of 19 patients who survived and 5 of 5 who died (AUROC = 1.0, P = 0.000047).

The researchers conclude that, if verified in bigger cohorts, blood protein tests could be beneficial in both identifying patients with the highest mortality risk and determining whether a specific treatment alters a patient’s expected trajectory.

Source: 10.1371/journal.pdig.0000007

Image Credit: Getty

You were reading: A single blood test can predict COVID-19 death risk weeks before outcome, study says